[{"id":343120,"last_updated":"2023-07-18 09:52:57","id_people":472289,"institutes":["ILC"],"type":"conference_article","type_order":5,"type_people":"conferenceObject","title":"Il Laboratorio di Filologia Collaborativa e Cooperativa (CoPhiLab) del CNR-ILC: dati, strumenti, servizi e infrastrutture","year":2022,"authors_people":"Federico Boschetti, Cosimo Burgassi, Riccardo Del Gratta, Angelo Mario Del Grosso, Elisa Guadagnini, Ouafae Nahli, Simone Zenzaro","authors_cnr":["Del Gratta, Riccardo","Guadagnini, Elisa","Boschetti, Federico","Del Grosso, Angelo Mario","Nahli, Ouafae","Burgassi, Cosimo","Zenzaro, Simone"],"authors_cnr_id":["11933","12720","14630","17769","18787","21104","21246"],"authors_cnr_institute":[""],"authors":["Boschetti, F.","Burgassi, C.","Del Gratta, R.","Del Grosso, A. M.","Guadagnini, E.","Nahli, O.","Zenzaro, S."],"abstract":"Questo contributo illustra le attivit\u00e0 e le risorse del Laboratorio di Filologia Collaborativa e Cooperativa (CoPhiLab) dell'Istituto di Linguistica Computazionale \"A. Zampolli\" del Consiglio Nazionale delle Ricerche (CNR-ILC), con particolare attenzione all'uso delle infrastrutture di ricerca nazionali e internazionali.","keywords":["Filologia Computazionale","Modelli Formali","Lingua Araba","Domain-Specific Languages","Ingegneria del Software"],"pages":"45-50","url":"https:\/\/www.eventi.garr.it\/it\/conf22","volume":"","doi":"10.26314\/GARR-Conf22-proceedings","editors_people":"Marta Mieli, Carlo Volpe","editors":["Mieli, M.","Volpe, C."],"published":"CONDIVISIONI La rete come strumento per costruire il futuro","publisher":"Associazione Consortium GARR (Roma, ITA)","issn":"","isbn":"978-88-946629-1-7","conference_name":"CondiVisioni. La rete come strumento per costruire il futuro","conference_place":"Palermo","conference_date":"18\/05\/2022-20\/05\/2022"},{"id":132459,"last_updated":"2023-07-24 08:25:25","id_people":458287,"institutes":["ILC","ISTI"],"type":"journal_article","type_order":0,"type_people":"article","title":"Challenges in the digital analysis of historical laminated manuscripts","year":2021,"authors_people":"Del Grosso A.M.; Fihri D.F.; Mohajir M. El; Tonazzini A.; Nahli O.","authors_cnr":["Del Grosso, Angelo Mario","Nahli, Ouafae","Tonazzini, Anna"],"authors_cnr_id":["17769","18787","20066"],"authors_cnr_institute":["048","048","074"],"authors":["Del Grosso, A. M.","Fihri, D. F.","Mohajir, M. E.","Tonazzini, A.","Nahli, O."],"abstract":"In this paper, we analyze and discuss the characteristics of a system for the effective digital preservation and fruition of historical manuscripts degraded by the process of lamination. The most significant degradation caused by lamination is that the parchment or paper support loses its flatness, and usually presents ripples and warnings. This, together with the affixed translucent varnish, dramatically impair the digital acquisition process, so that light reflections in the more disparate directions affect the digital images. A digital system to contrast this irreversible and progressive degradation and to enable an effective access to the fragile asset should provide a number of functionalities: specialized digitization, able to avoid reflections as much as possible; image enhancement, devised to correct the residual degradations and enhance the text for an easier legibility; semi-automatic transcription of the virtually restored pages; and, finally, scholarly encoding and linguistic analysis, which should adapt existing tools to the specificity of the primary source (writing system and language). As a case study, we will make reference to the \"Poem in Rajaz on medicine\", written by Abubacer in the XII century, and conserved in the Al Quaraouiyine Library located in Fez, Morocco. The feasibility study for the realization of such a system is of general utility, in that it can provide guidelines for the digitization, the enhancement and the text encoding of the many laminated manuscripts conserved in other historical archives. On the other hand, from the cultural heritage point of view, the experimentation on the \"Poem in Rajaz on medicine\" could foster the systematic philological and ontological study of a unique piece of our documental heritage: the longest poem of medieval Islamic medical literature.","keywords":["Cultural Heritage Digital Safeguard","Historical Manuscript Digitization","Document Image Processing","Linguistic Analysis","Ontological Analysis"],"pages":"34-43","url":"https:\/\/innove.org\/ijist\/index.php\/ijist\/article\/view\/190","volume":"5","doi":"10.57675\/IMIST.PRSM\/ijist-v5i1.190","editors_people":"","editors":[""],"published":"International Journal of Information Science and Technology","publisher":"[El Mohajir Mohammed] ([S. l. ], Marocco)","issn":"2550-5114","isbn":"","conference_name":"","conference_place":"","conference_date":""},{"id":132496,"last_updated":"2022-10-17 14:26:04","id_people":463930,"institutes":["ILC"],"type":"journal_article","type_order":0,"type_people":"article","title":"Structuring Arabic lexical and morphological resources using TEI: theory and practice","year":2021,"authors_people":"Ouafae Nahli; Angelo Mario Del Grosso","authors_cnr":["Del Grosso, Angelo Mario","Nahli, Ouafae"],"authors_cnr_id":["17769","18787"],"authors_cnr_institute":[""],"authors":["Nahli, O.","Del Grosso, A. M."],"abstract":"An Arabic word can be described according to its lexical and morphological information. The lexical information, conveyed by the root, consists of both semantic meaning and syntactic properties (e.g. parts of speech). The morphological information, encoded by patterns, is useful to group the words having similar syntactic, inflectional and semantic behaviour. Lexical analysis and morphological analysis have been separately described since the very first studies of the Arabic language. Although several scholarly works have illustrated Arabic lexicon models that encode semantic meanings, a systematic description of word patterns is still strongly lacking. In this work, we have implemented an exhaustive resource consisting of two levels: lexical and morphological. The lexical level collects information extracted from the dictionary al=q\u00afam\u00afus al=muh. \u00af?t.. The morphological level describes pattern formalization, which allows to enrich word descriptions with additional semantic, morphosyntactic and inflectional information. To build our digital resource, taking into account primary source, lexical requirements, and reusability, we followed the guidelines provided by the Text Encoding Initiative (abbreviated as TEI). In particular, we adopted the TEI module for the encoding of digital dictionaries and lexicons to formally represent the medieval al=q\u00afam\u00afus al=muh. \u00af?t. dictionary. Given the complexity of describing the morphological information present in the patterns, we also used the TEI module devoted to encoding feature structures. Consequently, we are building an exhaustive resource formed by the lexical and the morphological blocks. These two components are distinct but complementary resources where the lexical data are connected to morphological information. In addition, the morphological resource can be used as a stand-alone tool that allows the morphological analyzers to capture aspects of meaning that cannot be identified by current systems.","keywords":["classical Arabic dictionary","digital lexicography","al=q'"],"pages":"3-14","url":"https:\/\/innove.org\/ijist\/index.php\/ijist\/article\/view\/191","volume":"5","doi":"","editors_people":"","editors":[""],"published":"International Journal of Information Science and Technology","publisher":"[El Mohajir Mohammed] ([S. l. ], Marocco)","issn":"2550-5114","isbn":"","conference_name":"","conference_place":"","conference_date":""},{"id":132495,"last_updated":"2023-07-06 10:49:06","id_people":463923,"institutes":["ILC"],"type":"journal_article","type_order":0,"type_people":"article","title":"Commerce Num\u00e9rique: traffic signals for the crossroads between cultures","year":2021,"authors_people":"Ouafae Nahli; Antonietta Sanna; Michela Bandini; and Federico Boschetti","authors_cnr":["Bandini, Michela","Boschetti, Federico","Nahli, Ouafae"],"authors_cnr_id":["14630","18787"],"authors_cnr_institute":[""],"authors":["Nahli, O.","Sanna, A.","Bandini, M.","Boschetti, F."],"abstract":"Commerce is a literary French journal founded by Princess Margherita Caetani, involving three prestigious collaborators: Paul Val\u00e9ry, L\u00e9on-Paul Fargue, Val\u00e9ry Larbaud. It is composed by 29 volumes published between 1924 and 1932. Each volume collects different literary material of various well-known and unknown writers as poems or novels, translating some of the most important authors like Joyce, T.S. Eliot, Pirandello, Ungaretti, Saint-John Perse, Rilke, Hofmannsthal. Considering the historical, literary, and cultural importance of the Commerce journal, our project \"Commerce num\u00e9rique\" aims to digitize and to make the journal contents freely available online to both the general public and the research community. This article presents how the journal was encoded. Also, we give importance to the coding of poems present in Commerce. Indeed, some poems are original in another language and they are accompanied by their French translation. Other poems are a French-translated form without original text. In order to fully and accurately express the phenomena and their structures, we have adopted some aspects of the TEI framework, which we will explain in detail. Particular attention was paid to the French translation of a Moroccan Arabic poem from the 13th century. On the one hand, the original Arabic poetry is interesting because it presents some aspects of the Moroccan dialect and some aspects of the oral text. On the other hand, the study and the encoding of Arabic poetry in parallel to its translation highlight some important structural differences between Arabic poetry and Western poetry.","keywords":["Commerce Journal","OCR","TEI encoding","literary journal","digital resources","Arabic poetry"],"pages":"36-45","url":"https:\/\/innove.org\/ijist\/index.php\/ijist\/article\/view\/193","volume":"5","doi":"","editors_people":"","editors":[""],"published":"International Journal of Information Science and Technology","publisher":"[El Mohajir Mohammed] ([S. l. ], Marocco)","issn":"2550-5114","isbn":"","conference_name":"","conference_place":"","conference_date":""},{"id":132406,"last_updated":"2020-12-23 14:55:40","id_people":438041,"institutes":["ILC"],"type":"journal_article","type_order":0,"type_people":"article","title":"A New Rich Lexical Resource For Classical Arabic","year":2020,"authors_people":"MUSTAPHA KHALFI ARSALANE ZARGHILI OUAFAE NAHLI","authors_cnr":["Nahli, Ouafae"],"authors_cnr_id":["18787"],"authors_cnr_institute":[""],"authors":["Khalfi, M.","Zarghili, A.","Nahli, O."],"abstract":"Currently, large lexical resources are getting a high potential relevance for information systems and need of Lexical resources in Natural Language Processing (NLP) fields is paramount. To contribute meet these needs, we build a lexical resource from the famous dictionary al=q?m?s al=mu???(AQAM). Using a rule based approach, we have designed a system that allows extracting morpho-syntactical, semantics and lexical information from the famous dictionary. So, we obtained a digitized and structured version of AQAM, enriched by morpho-syntactical and lexical explicit information. In addition, the obtained resource is enriched by English translations of lemma and accompanying senses using a bilingual English-Arabic dictionary. Then we present an overview of an experiment alignment of the section of the letter b?\" on Princeton\"s WordNet (PWN) and Suggested Upper Merged Ontology (SUMO). This experience turned out to be interesting because it revealed that mapping an Arabic lexical resource on an English resource shows commonality between the two languages, but it allows especially to emphasize the non-equivalences between them. All obtained resources are represented in XML format anddistributed under free license","keywords":["Information Extraction Arabic Lexicon Al Qamus Al Muhit Machine-readable dictionary Arabic Lexical Resource"],"pages":"3863-3884","url":"https:\/\/www.ijact.in\/index.php\/ijact\/article\/view\/1196","volume":"Volume-IX, Issue-X","doi":"","editors_people":"","editors":[""],"published":"International journal of advanced computer science and technology","publisher":"Research India Publications (New Delhi, India)","issn":"2249-3123","isbn":"","conference_name":"","conference_place":"","conference_date":""},{"id":132404,"last_updated":"2023-07-24 08:38:26","id_people":439862,"institutes":["ILC","ISTI"],"type":"conference_article","type_order":5,"type_people":"conferenceObject","title":"Digital safeguard of laminated historical manuscripts: the treatise \"Poem in Rajaz on medicine\" as a case study","year":2020,"authors_people":"Del Grosso A.M.; Fassi Fihri D.; El Mohajir M.; Nahli O.; Tonazzini A.","authors_cnr":["Del Grosso, Angelo Mario","Nahli, Ouafae","Tonazzini, Anna"],"authors_cnr_id":["17769","18787","20066"],"authors_cnr_institute":["048","048","074"],"authors":["Del Grosso, A. M.","Fassi, F. D.","El Mohajir, M.","Nahli, O.","Tonazzini, A."],"abstract":"In this paper, we analyze and discuss the characteristics of a system for the effective digital preservation and fruition of historical manuscripts degraded by the process of lamination. As a case study, we will make reference to the \"Poem in Rajaz on medicine\", written by Abubacer in the XII century, and conserved in the Al Quaraouiyine Library located in Fez, Morocco. The conceived system should have at least four main functionalities: image acquisition (i.e. digitization), image enhancement, text encoding, and linguistic analysis. Based on the evaluation of the manuscript damages, the acquisition set up should be designed in such a way to be able to avoid reflections as much as possible. Suitable digital image processing techniques should also be devised to correct the residual degradations and enhance the text for an easier legibility. Finally, semi-automatic transcription, scholarly encoding and linguistic analysis, to be performed on the virtually restored pages, should adapt existing tools to the specificity of the primary source writing system and language. The feasibility study for the realization of such a system is of general utility, in that it can provide guidelines for the digitization, the enhancement and the text encoding of the many laminated manuscripts conserved in other historical archives. On the other hand, from the cultural heritage point of view, the experimentation on the \"Poem in Rajaz on medicine\" could foster the systematic philological and ontological study of a unique piece of our documental heritage: the longest poem of medieval Islamic medical literature.","keywords":["Cultural Heritage","Digital Safeguard","Historical Manuscript Digitization","Document Image Processing","Linguistic Analysis","Ontological Analysis"],"pages":"192-197","url":"https:\/\/ieeexplore.ieee.org\/document\/9357192","volume":"","doi":"10.1109\/CiSt49399.2021.9357192","editors_people":"","editors":[""],"published":"","publisher":"IEEE (New York, USA)","issn":"","isbn":"978-1-7281-6646-9","conference_name":"CiSt'2020-6th IEEE Congress on Information Science & Technology","conference_place":"Agadir-Essaouira, Morocco","conference_date":"June 5-12, 2021"},{"id":132405,"last_updated":"2023-07-27 11:22:59","id_people":439789,"institutes":["ILC"],"type":"conference_article","type_order":5,"type_people":"conferenceObject","title":"Creating Arabic Lexical Resources in TEI; A Schema for Discontinuous Morphology Encoding","year":2020,"authors_people":"Ouafae Nahli ; Angelo Mario Del Grosso","authors_cnr":["Del Grosso, Angelo Mario","Nahli, Ouafae"],"authors_cnr_id":["17769","18787"],"authors_cnr_institute":[""],"authors":["Nahli, O.","Del Grosso, A. M."],"abstract":"This article aims at formally grouping lexical and morphological information in order to obtain an electronic resource with respect to the Arabic language starting from the classical dictionary al=q?m?s al=mu???. This contribution examines practical aspects about the adoption of the guidelines provided by the Text Encoding Initiative (TEI) to encode the Arabic dictionary as a primary source. Moreover, the contribution points out a possible way to integrate semantic, morphological and syntactic information characterizing word patterns within the same TEI document. Specifically, the formalization of word patterns allows us to emphasize additional morphosyntactic regularities mainly concerning word distribution within sentences. Consequently, the obtained digital object represents both the medieval Arabic dictionary and a suitable resource that can be exploited for a number of Natural Language Processing tasks.","keywords":["classical Arabic dictionary","digital lexicography","al=q?m?s al=mu???","word patterns","TEI"],"pages":"9","url":"https:\/\/publications.cnr.it\/doc\/439789","volume":"","doi":"10.1109\/CiSt49399.2021.9357273","editors_people":"","editors":[""],"published":"","publisher":"IEEE (New York, USA)","issn":"","isbn":"978-1-7281-6646-9","conference_name":"IEEE-CIST2020 DPWH","conference_place":"Agadir-Essaouira, Morocco","conference_date":"5\/06\/2021-12\/06\/2021"},{"id":132403,"last_updated":"2020-12-22 09:58:09","id_people":439796,"institutes":["ILC"],"type":"conference_article","type_order":5,"type_people":"conferenceObject","title":"Digitizing and Encoding a Multilingual Literary Review: Commerce Numerique","year":2020,"authors_people":"Antonietta Sanna; Rachele Cinerari; Federico Boschetti; Ouafae Nahli","authors_cnr":["Boschetti, Federico","Nahli, Ouafae"],"authors_cnr_id":["14630","18787"],"authors_cnr_institute":[""],"authors":["Sanna, A.","Cinerari, R.","Boschetti, F.","Nahli, O."],"abstract":"Commerce was an important literary review founded in Paris by Princess Margherita Caetani, Prince Roffredo Caetani's wife. Born in America, she was polyglot and maecenas. Between 1924 and 1932 she surrounded herself with three prestigious collaborators: Paul Val\u00e9ry, L\u00e9on-Paul Fargue, Val\u00e9ry Larbaud. The review promoted the translation of World and European literature in French, translating some of the most important authors like Joyce, T.S. Eliot, Pirandello, Ungaretti, Saint-John Perse, Rilke, Hofmannsthal. The aim of this project is to promote by digitizing the dissemination of the review, to develop studies and research concerning the Caetani family's cultural activities in Europe. All the volumes of the literary review Commerce have been scanned, acquired by OCR and encoded in TEI-XML. The cultural value of the operation is discussed and the work-flow to create the digital textual corpus is described in detail.","keywords":["Review Commerce","OCR","TEI encoding","literary review","digital resources"],"pages":"4","url":"https:\/\/publications.cnr.it\/doc\/439796","volume":"","doi":"","editors_people":"","editors":[""],"published":"","publisher":"IEEE (New York, USA)","issn":"","isbn":"978-1-7281-6646-9","conference_name":"IEEE-CIST2020 DPWH","conference_place":"Agadir-Essaouira, Morocco","conference_date":"5\/06\/2021-12\/06\/2021"},{"id":132275,"last_updated":"2023-07-13 15:39:17","id_people":390296,"institutes":["ILC"],"type":"conference_article","type_order":5,"type_people":"conferenceObject","title":"Scanning is Just the Beginning: Exploiting Text and Language Technologies to Enhance the Value of Historical Manuscripts","year":2018,"authors_people":"Angelo Mario Del Grosso, Andrea Bellandi, Emiliano Giovannetti, Simone Marchi, Ouafae Nahli","authors_cnr":["Del Grosso, Angelo Mario","Nahli, Ouafae","Marchi, Simone","Giovannetti, Emiliano","Bellandi, Andrea"],"authors_cnr_id":["10442","11969","17627"],"authors_cnr_institute":[""],"authors":["Del Grosso, A. M.","Bellandi, A.","Giovannetti, E.","Marchi, S.","Nahli, O."],"abstract":"In this paper we present a digital process for the explicitation of the textual, linguistic and semantic content of historical manuscripts. The proposed workflow is composed of a sequence of incremental steps, each of which is described both on a methodological and practical perspective. The steps are: 1) visualization and structuring of metadata, 2) transcription, 3) structural encoding, 4) annotation, 5) lexical and conceptual structuring.","keywords":["Computational Lexica","Digital Scholarly Editing","Digital Humanities","al-Qamus al-Muhit"],"pages":"214-219","url":"https:\/\/publications.cnr.it\/doc\/390296","volume":"","doi":"10.1109\/CIST.2018.8596373","editors_people":"Al Achhab M., El Mohajir M., Jellouli I., El Mohajir B.E.","editors":["Al Achhab, M.","El Mohajir, M.","Jellouli, I.","El Mohajir, B. E."],"published":"Colloquium in Information Science and Technology, CIST","publisher":"IEEE (New York, USA)","issn":"","isbn":"978-1-5386-4385-3","conference_name":"CIST 2018 WH-MNLP","conference_place":"MARRAKECH, MOROCCO","conference_date":"21-27\/10\/2018"},{"id":132282,"last_updated":"2021-04-09 17:32:20","id_people":390504,"institutes":["ILC"],"type":"conference_article","type_order":5,"type_people":"conferenceObject","title":"ReadLet: Reading for Understanding","year":2018,"authors_people":"Marcello Ferro; Claudia Cappa; Sara Giulivi; Claudia Marzi; Ouafae Nahli; Franco Alberto Cardillo; Vito Pirrelli","authors_cnr":["Nahli, Ouafae","Pirrelli, Vito","Marzi, Claudia","Ferro, Marcello","Cardillo, Franco Alberto","Cappa, Claudia"],"authors_cnr_id":["326","8389","11870","17547","29386"],"authors_cnr_institute":[""],"authors":["Ferro, M.","Cappa, C.","Giulivi, S.","Marzi, C.","Nahli, O.","Cardillo, F. A.","Pirrelli, V."],"abstract":"This paper focuses on motivation, objectives, design issues and preliminary results of ReadLet, an ICT platform for assessing reading efficiency in primary school children. Test data are discussed on a sample of 200 early graders, reading French, Italian and Standard Modern Arabic (SMA).","keywords":["Reading","text comprehension","Specific Learning Disorders","multimodal signal processing","cloud computing","portable assistive technology"],"pages":"404-409","url":"https:\/\/publications.cnr.it\/doc\/390504","volume":"","doi":"","editors_people":"","editors":[""],"published":"","publisher":"IEEE (New York, USA)","issn":"","isbn":"978-1-5386-4385-3","conference_name":"IEEE-CIST2018 LED-ICT","conference_place":"Marrakech, Morocco","conference_date":"21-27\/10\/2018"},{"id":132269,"last_updated":"2021-04-08 15:06:48","id_people":388016,"institutes":["ILC"],"type":"conference_article","type_order":5,"type_people":"conferenceObject","title":"Evaluating Inflectional Complexity Crosslinguistically: a Processing Perspective","year":2018,"authors_people":"Marzi, C.; Ferro, M.; Nahli, O.; Belik, P.; Bompolas, S.; Pirrelli, V.","authors_cnr":["Pirrelli, Vito","Marzi, Claudia","Ferro, Marcello"],"authors_cnr_id":["326","8389","11870"],"authors_cnr_institute":[""],"authors":["Marzi, C.","Ferro, M.","Nahli, O.","Belik, P.","Bompolas, S.","Pirrelli, V."],"abstract":"The paper provides a cognitively motivated method for evaluating the inflectional complexity of a language, based on a sample of \"raw\" inflected word forms processed and learned by a recurrent self-organising neural network with fixed parameter setting. Training items contain no information about either morphological content or structure. This makes the proposed method independent of both meta-linguistic issues (e.g. format and expressive power of descriptive rules, manual or automated segmentation of input forms, number of inflectional classes etc.) and language-specific typological aspects (e.g. word-based, stem-based or template-based morphology). Results are illustrated by contrasting Arabic, English, German, Greek, Italian and Spanish.","keywords":["paradigm-based morphology","inflectional complexity","prediction-based processing","recurrent self-organising networks","Statistical And Machine Learning Methods","Language Modelling"],"pages":"3860-3866","url":"http:\/\/www.lrec-conf.org\/proceedings\/lrec2018\/summaries\/745.html","volume":"2018","doi":"","editors_people":"N. Calzolari, K. Choukri, C. Cieri, T. Declerck, S. Goggi, K. Hasida, H. Isahara, B. Maegaard, J. Mariani, H. Mazo, A. Moreno, J. Odijk, S. Piperidis & T. Tokunaga","editors":["Calzolari, N.","Choukri, K.","Cieri, C.","Declerck, T.","Goggi, S.","Hasida, K.","Isahara, H.","Maegaard, B.","Mariani, J.","Mazo, H.","Moreno, A.","Odijk, J.","Piperidis, S.","Tokunaga, T."],"published":"Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)","publisher":"European language resources association (ELRA) (Paris, FRA)","issn":"","isbn":"979-10-95546-00-9","conference_name":"Eleventh International Conference on Language Resources and Evaluation (LREC 2018)","conference_place":"Miyazaki, Japan","conference_date":"7-12\/05\/2018"},{"id":132281,"last_updated":"2019-01-07 16:55:27","id_people":390405,"institutes":["ILC"],"type":"conference_article","type_order":5,"type_people":"conferenceObject","title":"Arabic Language Alignment with English Ontologies-Some Ontological Reflections","year":2018,"authors_people":"Ouafae Nahli","authors_cnr":["Nahli, Ouafae"],"authors_cnr_id":[""],"authors_cnr_institute":[""],"authors":["Nahli, O."],"abstract":"There have been several attempts to build lexico-conceptual resources by extension of the English WordNet, i.e. by means of translation of English synsets. However, the extension approach is arguable because it assumes that the target resource is isomorphic to English WordNet. Yet, some languages, such as English and Arabic, can be very different. The problem would be to know, first, whether they conceptualize reality in the same way; and if not, to identify different concepts types. The mapping of a lexical resource of a different language onto Princeton WordNet of English (PWN) answers these questions. The experiment, in this article, describes results obtained from mapping the Arabic dictionary, al=q?m?s al=mu???, onto English WordNet and SUMO (Standard Upper Merged Ontology), also developed for the English language.","keywords":["Ontology","concept","Arabic","PWN","SUMO","al=q?m?s al=mu???"],"pages":"7","url":"https:\/\/publications.cnr.it\/doc\/390405","volume":"","doi":"","editors_people":"","editors":[""],"published":"","publisher":"IEEE (New York, USA)","issn":"","isbn":"978-1-5386-4385-3","conference_name":"CIST 2018 WH-MNLP","conference_place":"MARRAKECH, MAROCCO","conference_date":"21-27\/10\/2018"},{"id":132316,"last_updated":"2019-06-12 15:27:55","id_people":396593,"institutes":["IFC","ILC"],"type":"conference_misc","type_order":6,"type_people":"conferenceObject","title":"ReadLet: piattaforma ICT per valutare l'efficienza di lettura","year":2018,"authors_people":"Cappa, C.; Ferro, M.; Giulivi, S.; Marzi, C.; Nahli, O.; Cardillo, F.A.; Pirrelli, V.","authors_cnr":["Nahli, Ouafae","Pirrelli, Vito","Marzi, Claudia","Ferro, Marcello","Cardillo, Franco Alberto","Cappa, Claudia"],"authors_cnr_id":["326","8389","11870","17547","29386"],"authors_cnr_institute":[""],"authors":["Cappa, C.","Ferro, M.","Giulivi, S.","Marzi, C.","Nahli, O.","Cardillo, F. A.","Pirrelli, V."],"abstract":"ReadLet \u00e8 una piattaforma ICT pensata per valutare accuratamente l'efficienza di lettura nei bambini della scuola primaria. Combina tecnologia ICT portatile e cloud-computing\u009d con una serie di moduli software, specifici per modalit\u00e0 di somministrazione. Questi, implementati come servizi web, includono: i) valutazione dell'elaborazione del testo e della leggibilit\u00e0; ii) valutazione della velocit\u00e0 di lettura (ad alta voce e silente) e delle sue fluttuazioni); iii) valutazione della correttezza della decodifica ad alta voce; iv) valutazione della comprensione del testo (in lettura silente e da ascolto). Un prototipo della tecnologia ReadLet \u00e8 stato sperimentato su circa 200 alunni (8-11 anni), che variano per stato socio-economico, lingua (italiana, francese, araba) e area geografica (Italia, Svizzera, Marocco). L'utilizzo del tablet per la lettura \u00e8 stato percepito dai bambini come un'esperienza coinvolgente e piacevole. Gli insegnanti hanno trovato lo strumento facile da utilizzare e in grado di fornire maggiori informazioni rispetto agli strumenti tradizionali.","keywords":["leggere per capire","disturbi del linguaggio","screening"],"pages":"","url":"https:\/\/www.airipa.it\/congresso\/pluginfile.php\/2781\/mod_resource\/content\/1\/Programma%20Congresso%20AIRIPA_Arezzo_dettagliato-3.pdf","volume":"","doi":"","editors_people":"","editors":[""],"published":"","publisher":"","issn":"","isbn":"","conference_name":"XXVII Congresso Nazionale AIRIPA","conference_place":"Arezzo (Italy)","conference_date":"28-29\/09\/2018"},{"id":132283,"last_updated":"2018-09-17 16:37:46","id_people":390506,"institutes":["ILC"],"type":"thesis","type_order":11,"type_people":"doctoralThesis","title":"Vers une ontologie de la culture arabo-musulmane","year":2018,"authors_people":"Nahli Ouafae","authors_cnr":["Nahli, Ouafae"],"authors_cnr_id":[""],"authors_cnr_institute":[""],"authors":["Nahli, O."],"abstract":"Le projet vise \u00e0 d\u00e9crire les m\u00e9thodologies permettant de d\u00e9velopper un r\u00e9seau de connaissance pour la culture arabo-islamique sur la base d'un processus d'extractions automatiques de donn\u00e9es \u00e0 partir du lexique arabe al=qamus al=muHiT (qamus). Le choix de qamus est justifi\u00e9 par le fait qu'il a un statut d'autorit\u00e9 dans le monde arabe, au point que la parole qamus [oc\u00e9an] a supplant\u00e9 la parole mungid 'dictionnaire'. Le projet pr\u00e9voit divers \u00e9tapes de travail et, avant tout, l'acquisition d'une version num\u00e9rique de qamus. La mise au point d'algorithmes pour la codification partielle et automatique de la macrostructure lexicale et la conversion du lexique en format XML. D'autres algorithmes permettent l'identification de la microstructure lexicale et, l'annotation de chaque partie constituante de l'entr\u00e9e lexicale, entre autres, le lemme, sa nature morphologique, ses d\u00e9finitions, etc. En utilisant deux dictionnaires bilingues arabe-anglais, un syst\u00e8me de recherche permet de trouver, de mani\u00e8re automatique et quand c'est possible, la traduction de chaque lemme, ce qui permet de le lier au synset correspondant dans PWN et au concept de SUMO \u00e0 qui il pourrait faire r\u00e9f\u00e9rence. Une autre \u00e9tape serait l'analyse de divers \u00e9chantillons de lemmes pour d\u00e9tecter la validit\u00e9 des r\u00e9sultats.","keywords":["al qamus al muHiyT","ontologie","langue arabe","Wordnet","PWN","SUMO (The Suggested Upper Merged Ontology)"],"pages":"317","url":"https:\/\/publications.cnr.it\/doc\/390506","volume":"","doi":"","editors_people":"","editors":[""],"published":"","publisher":"","issn":"","isbn":"","conference_name":"","conference_place":"","conference_date":""},{"id":132146,"last_updated":"2018-08-23 10:41:58","id_people":363116,"institutes":["ILC"],"type":"journal_article","type_order":0,"type_people":"article","title":"Arabic word processing and morphology induction through adaptive memory self-organisation strategies","year":2017,"authors_people":"Marzi, C.; Ferro, M.; Nahli, O.","authors_cnr":["Nahli, Ouafae","Marzi, Claudia","Ferro, Marcello"],"authors_cnr_id":["8389","11870"],"authors_cnr_institute":[""],"authors":["Marzi, C.","Ferro, M.","Nahli, O."],"abstract":"Aim of the present study is to model the human mental lexicon, by focussing on storage and processing dynamics, as lexical organisation relies on the process of input recoding and adaptive strategies for long-term memory organisation. A fundamental issue in word processing is represented by the emergence of the morphological organisation level in the lexicon, based on paradigmatic relations between fully-stored word forms. Morphology induction can be defined as the task of perceiving and identifying morphological formatives within morphologically complex word forms, as a function of the dynamic interaction between lexical representations and distribution and degrees of regularity in lexical data. In the computational framework we propose here (TSOMs), based on Self-Organising Maps with Hebbian connections defined over a temporal layer, the identification\/perception of surface morphological relations involves the alignment of recoded representations of morphologically-related input words. Facing a non-concatenative morphology such as the Arabic inflectional system prompts a reappraisal of morphology induction through adaptive organisation strategies, which affect both lexical representations and long-term storage. We will show how a strongly adaptive self-organisation during training is conducive to emergent relations between word forms, which are concurrently, redundantly and competitively stored in human mental lexicon, and to generalising knowledge of stored words to unknown forms.","keywords":["Non-concatenative morphological structure","Lexical storage and access","Topological alignment","Synchronisation","Self-Organising Maps"],"pages":"179-188","url":"http:\/\/www.sciencedirect.com\/science\/article\/pii\/S1319157816301148","volume":"29","doi":"10.1016\/j.jksuci.2016.11.006","editors_people":"","editors":[""],"published":"Journal of King Saud University. Computer and information sciences (Online)","publisher":"Elsevier (Amsterdam, Paesi Bassi)","issn":"2213-1248","isbn":"","conference_name":"","conference_place":"","conference_date":""},{"id":132153,"last_updated":"2021-04-08 07:36:08","id_people":364353,"institutes":["ILC"],"type":"conference_article","type_order":5,"type_people":"conferenceObject","title":"An application of distributional semantics for the analysis of the Holy Quran","year":2016,"authors_people":"Giulia Benotto, Emiliano Giovannetti, Ouafae Nahli","authors_cnr":["Nahli, Ouafae","Benotto, Giulia","Giovannetti, Emiliano"],"authors_cnr_id":["11969"],"authors_cnr_institute":[""],"authors":["Benotto, G.","Giovannetti, E.","Nahli, O."],"abstract":"In this contribution we illustrate the methodology and the results of an experiment we conducted by applying Distributional Semantics Models to the analysis of the Holy Quran. Our aim was to gather information on the potential differences in meanings that the same words might take on when used in Modern Standard Arabic w.r.t. their usage in the Quran. To do so we used the Penn Arabic Treebank as a contrastive corpus.","keywords":["Distributional Semantics","the Holy Quran","Classical Arabic","Modern Standard Arabic","Contrastive Linguistics"],"pages":"374-379","url":"http:\/\/ieeexplore.ieee.org\/document\/7805074\/","volume":"","doi":"10.1109\/CIST.2016.7805074","editors_people":"El Mohajir, Mohammed and Chahhou, Mohamed and Al Achhab, Mohammed and El Mohajir, Badr Eddine","editors":["El Mohajir, M.","Chahhou, M.","Al Achhab, M.","El Mohajir, B. E."],"published":"2016 4th IEEE International Colloquium on Information Science and Technology (CiSt)","publisher":"","issn":"","isbn":"978-1-5090-0751-6","conference_name":"4th {IEEE} International Colloquium on Information Science and Technology, CiSt 2016","conference_place":"Tangier, Morocco","conference_date":"24-26\/10\/2016"},{"id":132115,"last_updated":"2018-08-23 10:41:03","id_people":355436,"institutes":["ILC"],"type":"conference_article","type_order":5,"type_people":"conferenceObject","title":"Al Qamus al Muhit, a Medieval Arabic Lexicon in LMF","year":2016,"authors_people":"Nahli O., Frontini F., Monachini M., Khan F., Zarghili A., Khalfi M.","authors_cnr":["Nahli, Ouafae","Khan, Anas Fahad","Monachini, Monica","Frontini, Francesca"],"authors_cnr_id":["8945","15911"],"authors_cnr_institute":["048","048","048","048"],"authors":["Nahli, O.","Frontini, F.","Monachini, M.","Khan, F.","Zarghili, A.","Khalfi, M."],"abstract":"This paper describes the conversion into LMF, a standard lexicographic digital format of 'al-q?m?s al-mu???, a Medieval Arabic lexicon. The lexicon is first described, then all the steps required for the conversion are illustrated. The work is will produce a useful lexicographic resource for Arabic NLP, but is also interesting per se, to study the implications of adapting the LMF model to the Arabic language. Some reflections are offered as to the status of roots with respect to previously suggested representations. In particular, roots are, in our opinion are to be not treated as lexical entries, but modeled as lexical metadata for classifying and identifying lexical entries. In this manner, each root connects all entries that are derived from it.","keywords":["Arabic Lexicon","LMF","Al Qamus al Muhi"],"pages":"943-950","url":"http:\/\/www.lrec-conf.org\/proceedings\/lrec2016\/index.html","volume":"","doi":"","editors_people":"Nicoletta Calzolari (Conference Chair), Khalid Choukri, Thierry Declerck, Sara Goggi, Marko Grobelnik, Bente Maegaard, Joseph Mariani, H\u00e9l\u00e8ne Mazo, Asunci\u00f3n Moreno, Jan Odijk, Stelios Piperidis","editors":["Calzolari, N.","Choukri, K.","Declerck, T.","Goggi, S.","Grobelnik, M.","Maegaard, B.","Mariani, J.","Mazo, H.","Moreno, A.","Odijk, J.","Piperidis, S."],"published":"","publisher":"European Language Resources Association ELRA (Paris, FRA)","issn":"","isbn":"978-2-9517408-9-1","conference_name":"Tenth International Conference on Language Resources and Evaluation (LREC 2016)","conference_place":"Portoroz, Slovenia","conference_date":"23-28 may"},{"id":132150,"last_updated":"2018-08-23 10:39:30","id_people":363709,"institutes":["ILC"],"type":"conference_misc","type_order":6,"type_people":"conferenceObject","title":"Il corpus di testi arabi in Memorata Poetis","year":2016,"authors_people":"Ouafae Nahli, Federico Boschetti, Silvia Arrigoni, Luigi Tessarolo","authors_cnr":["Nahli, Ouafae","Boschetti, Federico"],"authors_cnr_id":["14630"],"authors_cnr_institute":[""],"authors":["Nahli, O.","Boschetti, F.","Arrigoni, S.","Tessarolo, L."],"abstract":"","keywords":["letteratura araba","temi e motivi"],"pages":"157-162","url":"http:\/\/www.himeros.eu\/aiucd2016\/c03.pdf","volume":"","doi":"","editors_people":"Federico Boschetti","editors":["Boschetti, F."],"published":"AIUCD 2016-Book of Abstracts","publisher":"","issn":"","isbn":"","conference_name":"Quinto Convegno Annuale AIUCD. Edizioni digitali: rappresentazione, interoperabilit\u00e0, analisi del testo e infrastrutture","conference_place":"Ca' Dolfin, Venezia, Italia","conference_date":"7-9\/9\/2016"},{"id":132271,"last_updated":"2018-09-17 16:50:36","id_people":390724,"institutes":["ILC"],"type":"misc","type_order":12,"type_people":"other","title":"Corpus dei testi arabi in \"Memorata Poestis\"","year":2016,"authors_people":"Nahli Ouafae","authors_cnr":["Nahli, Ouafae"],"authors_cnr_id":[""],"authors_cnr_institute":[""],"authors":["Nahli, O."],"abstract":"Corpus epigrafico arabo, per motivi didattici e scientifici, i testi sono stati vocalizzati e tradotti in italiano.","keywords":["Poesia","Epigrafi","Memorata Poetis","lingua araba"],"pages":"","url":"http:\/\/www.memoratapoetis.it\/public\/","volume":"","doi":"","editors_people":"","editors":[""],"published":"","publisher":"","issn":"","isbn":"","conference_name":"","conference_place":"","conference_date":""},{"id":132096,"last_updated":"2023-07-07 17:53:55","id_people":342436,"institutes":["ILC"],"type":"conference_article","type_order":5,"type_people":"conferenceObject","title":"Improved Written Arabic Word Parsing through Orthographic, Syntactic and Semantic constraints","year":2015,"authors_people":"Ouafae Nahli, Simone Marchi","authors_cnr":["Nahli, Ouafae","Marchi, Simone"],"authors_cnr_id":["10442"],"authors_cnr_institute":[""],"authors":["Nahli, O.","Marchi, S."],"abstract":"The script-based and morphological characteristics of the Arabic language increase considerably the number of alternative analyses output by any morphological parser that does not use orthographic, syntactic and semantic constraints. In order to reduce time-wasting and error-prone proliferation of multiple outputs to be filtered in a post-processing phase, we have tried to optimize word processing by providing the morphological parser with multiple levels of information. We have operated at three such levels: orthography, morpho-syntax and semantics.","keywords":["Arabic Language","Arabic NLP","Orthography","Morpho-syntax","Semantics"],"pages":"210-214","url":"http:\/\/www.aaccademia.it\/elenco-libri?aaref=CLIC_2015","volume":"","doi":"","editors_people":"","editors":[""],"published":"","publisher":"Accademia University Press (Torino, ITA)","issn":"","isbn":"9788899200626","conference_name":"Second Italian Conference on Computational Linguistics CLiC-it 2015","conference_place":"Trento","conference_date":"3-4 Dicembre 2015"},{"id":132079,"last_updated":"2015-09-29 13:48:02","id_people":333414,"institutes":["ILC"],"type":"conference_article","type_order":5,"type_people":"conferenceObject","title":"Computational Linguistics and Language Physiology: Insights from Arabic NLP and Cooperative Editing","year":2015,"authors_people":"Pirrelli, Vito; Nahli, Ouafae; Boschetti, Federico; Del Gratta, Riccardo; Marzi, Claudia","authors_cnr":["Nahli, Ouafae","Pirrelli, Vito","Marzi, Claudia","Del Gratta, Riccardo","Boschetti, Federico"],"authors_cnr_id":["326","8389","11933","14630"],"authors_cnr_institute":["048","048","048","048","048"],"authors":["Pirrelli, V.","Nahli, O.","Boschetti, F.","Del Gratta, R.","Marzi, C."],"abstract":"Computer processing of written Arabic raises a number of challenges to traditional parsing architectures on many levels of linguistic analysis. In this contribution, we review some of these core issues and the demands they make, to suggest different strategies to successfully tackle them. In the end, we assess these issues in connection with the behaviour of neuro-biologically inspired lexical architectures known as Temporal Self-Organising Maps. We show that, far from being language-specific problems, issues in Arabic processing can shed light on some fundamental characteristics of the human language processor, such as structure-based lexical recoding, concurrent, competitive activation of output candidates and dynamic selection of optimal solutions.","keywords":["Non-concatenative morphology","Optical Character Recognition","WordNet","Temporal Self-organising Maps","Mental Lexicon","Language neuro-physiology"],"pages":"1-8","url":"http:\/\/dl.acm.org\/citation.cfm?id=2802612","volume":"","doi":"10.1145\/2802612.2802637","editors_people":"Francesca Tomasi, Roberto Rosselli Del Turco, Anna Maria Tammaro","editors":["Tomasi, F.","Del Turco, R. R.","Tammaro, A. M."],"published":"Third AIUCD Annual Conference-Humanities and Their Methods in the Digital Ecosystem","publisher":"","issn":"","isbn":"978-1-4503-3295-8","conference_name":"Third AIUCD Annual Conference-Humanities and Their Methods in the Digital Ecosystem","conference_place":"Bologna (IT)","conference_date":"18-19\/09\/2014"},{"id":131657,"last_updated":"2015-12-11 11:17:58","id_people":295474,"institutes":["ILC"],"type":"conference_misc","type_order":6,"type_people":"conferenceObject","title":"Collaborative Philology on the way to Web Services: the case of CoPhiWordnet","year":2015,"authors_people":"Federico Boschetti, Riccardo Del Gratta, Angelo Del Grosso, Monica Monachini, Harry Diakoff, and Ouafae Nahli","authors_cnr":["Del Gratta, Riccardo","Del Grosso, Angelo Mario","Nahli, Ouafae","Monachini, Monica","Boschetti, Federico"],"authors_cnr_id":["8945","14630"],"authors_cnr_institute":["048","048","048","048","048"],"authors":["Boschetti, F.","Del Gratta, R.","Del Grosso, A.","Monachini, M.","Diakoff, H.","Nahli, O."],"abstract":"Starting from previous initiatives of the CoPhiLab, we show how they can be reinterpreted as Web Services, especially when they become part of a wider scenario: Web Services are used to make connections between lexicons, semantic resources and a fine grained text management. Linked Open Data is chosen to be the paradigm used to link the dierent resources, but also as the modality of data presentation.","keywords":["Collaborative Philology","Web Services","Linked Open Data","Text Services","Text Interpretation"],"pages":"","url":"http:\/\/langrid.org\/wlsi2015\/program.html","volume":"","doi":"","editors_people":"","editors":[""],"published":"","publisher":"","issn":"","isbn":"","conference_name":"The Second International Workshop on Worldwide Language Service Infrastructure, WLSI 2015","conference_place":"Kyoto","conference_date":"22-23rd January 2015"},{"id":132292,"last_updated":"2020-09-11 14:10:38","id_people":390659,"institutes":["ILC"],"type":"misc","type_order":12,"type_people":"other","title":"Banca dati testuale Greek into Arabic","year":2015,"authors_people":"Cristina D'Ancona, Andrea Bozzi, Ouafae Nahli, Margherita Farina, Elisa Coda, Federico Boschetti, Angelo Mario Del Grosso, Simone Marchi","authors_cnr":["Del Grosso, Angelo Mario","Nahli, Ouafae","Bozzi, Andrea","Marchi, Simone","Boschetti, Federico"],"authors_cnr_id":["2866","10442","14630"],"authors_cnr_institute":[""],"authors":["D'Ancona, C.","Bozzi, A.","Nahli, O.","Farina, M.","Coda, E.","Boschetti, F.","Del Grosso, A. M.","Marchi, S."],"abstract":"Banca dati testuale con la codifica XML della pericopatura dei testi Greco-Arabo di alcuni trattati delle Enneadi di Plotino.","keywords":["Digital Humanities","Computational Philology","Greek into Arabic","http: \/\/g2a. ilc. cnr. it"],"pages":"","url":"http:\/\/g2a.ilc.cnr.it\/","volume":"","doi":"","editors_people":"","editors":[""],"published":"","publisher":"","issn":"","isbn":"","conference_name":"","conference_place":"","conference_date":""},{"id":132294,"last_updated":"2018-09-17 16:38:15","id_people":390722,"institutes":["ILC"],"type":"misc","type_order":12,"type_people":"other","title":"Banca dati dell'analisi morfo-sintattica del testo \"Afl\u016b\u1e6d\u012bn \u02bbinda al-\u02bbArab\", \u02bbAbd al-Rah\u0323ma\u0304n Badawi\u0304, Cairo 1955, 1966","year":2015,"authors_people":"Ouafae Nahli","authors_cnr":["Nahli, Ouafae"],"authors_cnr_id":[""],"authors_cnr_institute":[""],"authors":["Nahli, O."],"abstract":"Banca dati testuali con l'analisi morfo-sintattica del testo \"Afl???n ?inda l-?Arab\"; editore ?A. Badaw?, D?r al-Nah?at al-?arabiyya, Cairo 1966","keywords":["analisi morfo-sintattica","Lingua araba","Greek Into Arabic"],"pages":"","url":"http:\/\/g2a.ilc.cnr.it:8080\/Teologia_Wapp\/Home.xhtml?centerPage=teologia","volume":"","doi":"","editors_people":"","editors":[""],"published":"","publisher":"","issn":"","isbn":"","conference_name":"","conference_place":"","conference_date":""},{"id":132295,"last_updated":"2018-10-19 16:01:46","id_people":390727,"institutes":["ILC"],"type":"misc","type_order":12,"type_people":"other","title":"Aggiornamenti banca dati del Motore morfologico Aramorph","year":2015,"authors_people":"Ouafae Nahli","authors_cnr":["Nahli, Ouafae"],"authors_cnr_id":[""],"authors_cnr_institute":[""],"authors":["Nahli, O."],"abstract":"AraMorph's components are essentially two: the rule engine for morphological analysis and a repository of linguistic resources mainly composed of three lexicons: i) the dictStems lexicon, which contains 38.600 lemmas; ii) the dictPrefixes lexicon, which consists of sequences of proclitics and inflectional prefixes; iii) the dictSuffixes lexicon, which consists of sequences of inflectional suffixes and enclitics. These lexica are accompanied by three compatibility tables used for checking combinations of A (proclitics+prefixes), B (stems) and C (suffixes+enclitics). To cut down on arabic parse overgeneration, one has to enforce further restrictions in compatibility tables, e.g. the verb's ability to accept nominative and accusative pronouns, and to select a rational subject. We then augmented verb entries with subcategorization information such as case assignment and the restriction on rational subjects. At the same time, it was necessary to update compatibility tables.","keywords":["analisi morfo-sintattica","Lingua araba","Aramorph"],"pages":"","url":"http:\/\/hdl.handle.net\/20.500.11752\/ILC-94","volume":"","doi":"","editors_people":"","editors":[""],"published":"","publisher":"","issn":"","isbn":"","conference_name":"","conference_place":"","conference_date":""},{"id":132030,"last_updated":"2016-03-30 12:09:26","id_people":318313,"institutes":["ILC"],"type":"conference_article","type_order":5,"type_people":"conferenceObject","title":"Enhancing Arabic WordNet with the use on Princeton WordNet and a bilingual dictionary","year":2014,"authors_people":"Del Gratta Riccardo; Ouafae Nahli","authors_cnr":["Nahli, Ouafae","Del Gratta, Riccardo"],"authors_cnr_id":["11933"],"authors_cnr_institute":["048","048"],"authors":["Del Gratta, R.","Nahli, O."],"abstract":"This paper describes an heuristic-based approach to enhance existing WordNets with freely available bilingual resources. The approach has been applied to the Arabic WordNet using the AraMorph bilingual dictionary as bilingual resource, but its guidelines are quite general to be effectively applied to other languages. The English words extracted from the bilingual resource are checked against Princeton WordNet in order to quantify their coverage and to select only those words which share the same set of synsets. This strongly reduces the number of Arabic words of the pairs. These latter are then checked against the Arabic WordNet to make new words emerge and -possibly- add new synonyms.","keywords":["WordNet","Arabic","English","Bilingual Resource","Enhancement"],"pages":"278-284","url":"http:\/\/ieeexplore.ieee.org\/stamp\/stamp.jsp?tp=&arnumber=7016632","volume":"","doi":"10.1109\/CIST.2014.7016632","editors_people":"","editors":[""],"published":"3rd International IEEE Colloquium on Information Science and Technology; From 20th to 22nd of October 2014 Tetuan-Chefchaouen Morocco","publisher":"IEEE Communications Society (Piscataway, USA)","issn":"","isbn":"978-1-4799-5978-5","conference_name":"ANLP IEEE CIST14","conference_place":"Tetuan, Morocco","conference_date":"20-22\/10\/ 2014"},{"id":131995,"last_updated":"2015-01-26 15:50:29","id_people":295187,"institutes":["ILC"],"type":"conference_article","type_order":5,"type_people":"conferenceObject","title":"Towards a flexible open-source software library for multi-layered scholarly textual studies: An Arabic case study dealing with semi-automatic language processing","year":2014,"authors_people":"Del Grosso A. M.; Nahli O.","authors_cnr":["Del Grosso, Angelo Mario","Nahli, Ouafae"],"authors_cnr_id":[""],"authors_cnr_institute":[""],"authors":["Del Grosso, A. M.","Nahli, O."],"abstract":"This paper presents both the general model and a case study of the Computational and Collaborative Philology Library (CoPhiLib), an ongoing initiative underway at the Institute for Computational Linguistics (ILC) of the National Research Council (CNR), Pisa, Italy. The library, designed and organized as a reusable, abstract and open-source software component, aims at solving the needs of multi-lingual and cross-lingual analysis by exposing common Application Programming Interfaces (APIs). The core modules, coded by the Java programming language, constitute the groundwork of a Web platform designed to deal with textual scholarly needs. The Web application, implemented according to the Java Enterprise specifications, focuses on multi-layered analysis for the study of literary documents and related multimedia sources. This ambitious challenge seeks to obtain the management of textual resources, on the one hand by abstracting from current language, on the other hand by decoupling from the specific requirements of single projects. This goal is achieved thanks to methodologies declared by the \"agile process\", and by putting into effect suitable use case modeling, design patterns, and component-based architectures. The reusability and flexibility of the system have been tested on an Arabic case study: the system allows users to choose the morphological engine (such as AraMorph or Al-Khalil), along with linguistic granularity (i.e. with or without declension). Finally, the application enables the construction of annotated resources for further statistical engines (training set).","keywords":["Design","Information Engineering","Design Patterns","Text Processing","Arabic Natural Language Processing"],"pages":"285-290","url":"http:\/\/ieeexplore.ieee.org\/xpl\/articleDetails.jsp?tp=&arnumber=7016633&queryText%3Ddel+grosso+philology","volume":"","doi":"10.1109\/CIST.2014.7016633","editors_people":"M. El Mohajir, M. Al Achhab, M. Chahhou, A. Mounir, B. El Mohajir, V. Pirrelli, A. Zarghili, M. ElFar","editors":["El Mohajir, M.","Al Achhab, M.","Chahhou, M.","Mounir, A.","El Mohajir, B.","Pirrelli, V.","Zarghili, A.","Elfar, M."],"published":"IEEE Cinference Publications-Catalog Number: CFP1467R-ART","publisher":"IEEE (New York, USA)","issn":"","isbn":"978-1-4799-5978-5","conference_name":"Third IEEE International Colloquium in Information Science and Technology (CIST)","conference_place":"Tetuan, Morocco","conference_date":"20-22\/10\/2014"},{"id":131994,"last_updated":"2016-03-18 12:01:28","id_people":295178,"institutes":["ILC"],"type":"conference_article","type_order":5,"type_people":"conferenceObject","title":"Word Processing for Arabic Language: A reappraisal of morphology induction through adaptive memory self-organisation strategies","year":2014,"authors_people":"Marzi, Claudia; Nahli, Ouafae; Ferro, Marcello","authors_cnr":["Nahli, Ouafae","Marzi, Claudia","Ferro, Marcello"],"authors_cnr_id":["8389","11870"],"authors_cnr_institute":["048","048","048"],"authors":["Marzi, C.","Nahli, O.","Ferro, M."],"abstract":"Modelling the mental lexicon focuses on processing and storage dynamics, since lexical organisation relies on the process of input recoding and adaptive strategies for long-term memory organisation. A fundamental issue in word processing is represented by the emergence of the morphological organisation level in the lexicon, based on paradigmatic relations between fully-stored word forms. Morphology induction can be defined as the task of identifying morphological formatives within morphologically complex word forms. In the computational framework we propose here (TSOMs), based on Self-Organising Maps with Hebbian connections defined over a temporal layer, the identification\/perception of surface morphological relations involves the alignment of recoded representations of morphologically-related input words. Facing a non-concatenative morphology such as the Arabic inflectional system prompts a reappraisal of morphology induction through adaptive organisation strategies, which affect both lexical representations and long-term storage. We will show how a strongly adaptive self-organisation during training is conducive to emergent relations between stored word forms, and to high accuracy rates in generalising knowledge of stored words to unknown forms.","keywords":["Non-concatenative morphological structure","lexical storage and access","SOMs","word recoding and processing","adaptive strategies","morphology"],"pages":"241-247","url":"http:\/\/ieeexplore.ieee.org\/xpl\/articleDetails.jsp?arnumber=7016626&punumber%3D6996097","volume":"","doi":"10.1109\/CIST.2014.7016626","editors_people":"M. El Mohajir, M. Al Achhab, M. Chahhou, A. Mounir, B. El Mohajir, V. Pirrelli, A. Zarghili, M. ElFar","editors":["El Mohajir, M.","Al Achhab, M.","Chahhou, M.","Mounir, A.","El Mohajir, B.","Pirrelli, V.","Zarghili, A.","Elfar, M."],"published":"IEEE Conference Publications-Catalog Number: CFP1467R-ART","publisher":"IEEE (New York, USA)","issn":"","isbn":"978-1-4799-5979-2","conference_name":"Third IEEE International Colloquium in Information Science and Technology (CIST)","conference_place":"Tetuan (Morocco)","conference_date":"20-22\/10\/2014"},{"id":131959,"last_updated":"2015-01-07 20:06:14","id_people":288372,"institutes":["ILC"],"type":"conference_misc","type_order":6,"type_people":"conferenceObject","title":"Modelli, metodi e strumenti per il trattamento automatico della lingua araba e per l'editing in ambienti collaborativi","year":2014,"authors_people":"Boschetti, Federico; Del Gratta, Riccardo; Marzi, Claudia; Nahli, Ouafae; Pirrelli, Vito","authors_cnr":["Nahli, Ouafae","Pirrelli, Vito","Marzi, Claudia","Del Gratta, Riccardo","Boschetti, Federico"],"authors_cnr_id":["326","8389","11933","14630"],"authors_cnr_institute":["048","048","048","048","048"],"authors":["Boschetti, F.","Del Gratta, R.","Marzi, C.","Nahli, O.","Pirrelli, V."],"abstract":"La linguistica computazionale ha portato negli ultimi vent'anni a un profondo mutamento nello studio delle lingue e delle loro testimonianze scritte, spostando l'accento della ricerca da aspetti linguistico-formali all'uso linguistico in contesti comunicativi reali. Il presente contributo illustra l'impatto di questo cambio di prospettiva sullo studio della lingua araba, attraverso una rassegna di alcune attivit\u00e0 di ricerca in corso presso l'Istituto di Linguistica Computazionale del CNR di Pisa: I. acquisizione dei testi arabi tramite Optical Character Recognition (OCR) e sviluppo di strumenti per la correzione manuale del testo in ambienti collaborativi; II. sviluppo di algoritmi e strumenti per l'analisi morfologica della lingua araba; III. analisi delle dinamiche di acquisizione del lessico arabo mediante architetture bio-computazionali; IV. sviluppo della WordNet dell'Arabo collegata a Princeton WordNet, ItalWordNet, LatinWordNet e alla nascente AncientGreek WordNet. Queste attivit{ sono rivolte sia all'analisi delle caratteristiche linguistiche dell'arabo che allo studio della produzione letteraria araba e dei suoi rapporti storico-culturali con altre lingue. In particolare, il contributo intende illustrare la fertilit\u00e0 di un approccio metodologico che metta in relazione le dinamiche di acquisizione del lessico arabo, con la messa a punto di procedure di analisi ed edizione critica del testo e con i principi di organizzazione ontologica di una lingua ad alta produttivit\u00e0 derivazionale.","keywords":[""],"pages":"","url":"http:\/\/aiucd2014.unibo.it\/book-of-abstracts.pdf","volume":"","doi":"","editors_people":"Federica Rossi, Francesca Tomasi","editors":["Rossi, F.","Tomasi, F."],"published":"La metodologia della ricerca umanistica nell'ecosistema digitale-AIUCD 2014 Terzo convegno annuale","publisher":"","issn":"","isbn":"","conference_name":"AIUCD 3rd annual conference","conference_place":"Bologna","conference_date":"18-19 settembre 2014"},{"id":131937,"last_updated":"2015-04-22 15:36:17","id_people":288058,"institutes":["ILC"],"type":"conference_misc","type_order":6,"type_people":"conferenceObject","title":"A top-down approach to the design of components for the philological domain","year":2014,"authors_people":"Federico Boschetti, Angelo Mario Del Grosso, Anas Fahad Khan, Marion Lam\u00e9, Ouafae Nahli","authors_cnr":["Del Grosso, Angelo Mario","Nahli, Ouafae","Khan, Anas Fahad","Lam\u00e9, Marion","Boschetti, Federico"],"authors_cnr_id":["14630"],"authors_cnr_institute":["048","048","048","048","048"],"authors":["Boschetti, F.","Del Grosso, A. M.","Khan, A. F.","Lam\u00e9, M.","Nahli, O."],"abstract":"This paper focuses on the methodology applied to the development of components in the domain of collaborative philology in the Memorata Poetis Project. This initiative, led by the University of Venice, coordinates eight units sharing the same cyber-infrastructure and is co-funded by the Italian Ministry of Instruction, University and Research (PRIN 2010\/11). The project aims to study the multilingual intertextuality between epigraphic texts and literary epigrams, the transmission of themes, motives, etc. between different communicative situations (epigraphic versus literary) and different civilisations (Greek, Latin and Italian). As a control group, we analyse a corpus of epigraphic and literary texts in Arabic which do not belong to the same tradition as the others. The study of intertextuality affects both the reconstruction of the text (constitutio textus), by providing variants from the indirect tradition, and its interpretation (interpretatio), by widening the contexts in which the text has been reused.","keywords":[""],"pages":"","url":"https:\/\/publications.cnr.it\/doc\/288058","volume":"","doi":"","editors_people":"","editors":[""],"published":"Digital Humanities 2014-Book of Abstracts","publisher":"","issn":"","isbn":"","conference_name":"DH2014","conference_place":"Lausanne","conference_date":"8-12 july 2014"},{"id":132407,"last_updated":"2020-12-23 14:59:14","id_people":288053,"institutes":["ILC"],"type":"conference_misc","type_order":6,"type_people":"conferenceObject","title":"Towards a flexible open-source software library for multi-layered scholarly textual studies-An Arabic use-case dealing with semi-automatic language processing","year":2014,"authors_people":"Angelo Mario Del Grosso, Ouafae Nahli","authors_cnr":["Del Grosso, Angelo Mario","Nahli, Ouafae"],"authors_cnr_id":[""],"authors_cnr_institute":["048","048"],"authors":["Del Grosso, A. M.","Nahli, O."],"abstract":"This paper presents both the general model and a case study of the Computational and Collaborative Philology Library (CoPhiLib), an ongoing initiative underway at the Institute for Computational Linguistics (ILC) of the National Research Council (CNR), Pisa, Italy. The library, designed and organized as a reusable, abstract and open-source software component, aims at solving the needs of multi-lingual and cross- lingual analysis by exposing common Application Programming Interfaces (APIs). The core modules, coded by the Java programming language, constitute the groundwork of a Web platform designed to deal with textual scholarly needs. The Web application, implemented according to the Java Enterprise specifications, focuses on multi-layered analysis for the study of literary documents and related multimedia sources. This ambitious challenge seeks to obtain the management of textual resources, on the one hand by abstracting from current language, on the other hand by decoupling from the specific requirements of single projects. This goal is achieved thanks to methodologies declared by the \"agile process\", and by putting into effect suitable use case modeling, design patterns, and component- based architectures. The reusability and flexibility of the system have been tested on an Arabic case study: the system allows users to choose the morphological engine (such as AraMorph or Al- Khalil), along with linguistic granularity (i.e. with or without declension). Finally, the application enables the construction of annotated resources for further statistical engines (training set).","keywords":["Computational and collaborative philology","API"],"pages":"","url":"https:\/\/publications.cnr.it\/doc\/288053","volume":"","doi":"","editors_people":"","editors":[""],"published":"","publisher":"","issn":"","isbn":"","conference_name":"ANLP IEEE CIST14","conference_place":"Tetuan, Morocco","conference_date":"20-22\/10\/ 2014"},{"id":131966,"last_updated":"2018-08-23 11:04:10","id_people":288546,"institutes":["ILC"],"type":"journal_article","type_order":0,"type_people":"article","title":"Computational contributions for Arabic language processing Part I. The automatic morphologic analysis of Arabic texts","year":2013,"authors_people":"Nahli, Ouafae","authors_cnr":["Nahli, Ouafae"],"authors_cnr_id":[""],"authors_cnr_institute":[""],"authors":["Nahli, O."],"abstract":"problems of ambiguity inherent to the Arabic language. Difficulties arose in the various stages of automatic processing of the Arabic version of Plotinus, the text which lies at the core of our project. Part I highlights the needs that led us to update the morphological engine AraMorph in order to optimize its morpho-syntactic analysis. Even if the engine has been optimized, a digital lexical source for better use of the system is still lacking. Part II presents a methodology exploiting the internal structure of the Arabic lexicographic encyclopaedia Lisan al-\"arab, which allows automatic extraction of the roots and derived lemmas. The outcome of this work is a useful resource for morphological analysis of Arabic, either in its own right, or to enrich already existing resources","keywords":["Morphological engine AraMorph","Morpho-syntactic analysis","Arabic language"],"pages":"195-206","url":"http:\/\/www.greekintoarabic.eu\/uploads\/media\/NAHLI_SGA_3-2013.pdf","volume":"3","doi":"","editors_people":"","editors":[""],"published":"Studia graeco-arabica","publisher":"Pacini Editore (Pisa, Italia)","issn":"2281-2687","isbn":"","conference_name":"","conference_place":"","conference_date":""},{"id":131973,"last_updated":"2016-03-14 09:59:00","id_people":282561,"institutes":["ILC"],"type":"journal_article","type_order":0,"type_people":"article","title":"Computational contributions for Arabic language processing-Part II. Lisan al-'arab as a source of lexical and morphological knowledge","year":2013,"authors_people":"Ouafae Nahli, Emiliano Giovannetti","authors_cnr":["Nahli, Ouafae","Giovannetti, Emiliano"],"authors_cnr_id":["11969"],"authors_cnr_institute":["048","048"],"authors":["Nahli, O.","Giovannetti, E."],"abstract":"The following sections illustrate a part of the study on the morphology of the Arabic language which is carried on within the framework of the ERC project Greek into Arabic. Philosophical Concepts and Linguistic Bridges ADG 249431. We used the Arabic lexicographic encyclopaedia Lisan al-'arab and, thanks to the regularity of its structure, we developed a system for the extraction of morphologically labelled word sequences, to be exploited for morphological analysis purposes.","keywords":["Arabic morphology","Arabic morphological analysis","Arabic lexicography","Natural Language Processing"],"pages":"207-210","url":"https:\/\/publications.cnr.it\/doc\/282561","volume":"3","doi":"","editors_people":"","editors":[""],"published":"Studia graeco-arabica","publisher":"CNR, Istituto di Linguistica Computazionale (Pisa, Italia)","issn":"2239-012X","isbn":"","conference_name":"","conference_place":"","conference_date":""},{"id":132296,"last_updated":"2020-09-11 14:10:53","id_people":390781,"institutes":["ILC"],"type":"technical_report","type_order":8,"type_people":"report","title":"Greek into Arabic: contents, technologies and (humanistic and scientific) applications of a new software","year":2012,"authors_people":"Andrea Bozzi, Emiliano Giovannetti, Federico Boschetti, Ouafae Nahli, Simone Marchi, Silvia Piccini, Nilda Ruimy e Angelo Mario Del Grosso.","authors_cnr":["Piccini, Silvia","Del Grosso, Angelo Mario","Nahli, Ouafae","Bozzi, Andrea","Marchi, Simone","Giovannetti, Emiliano","Boschetti, Federico","Ruimy, Nilda"],"authors_cnr_id":["2866","10442","11969","14630","18402"],"authors_cnr_institute":[""],"authors":["Bozzi, A.","Giovannetti, E.","Boschetti, F.","Nahli, O.","Marchi, S.","Piccini, S.","Ruimy, N.","Del Grosso, A. M."],"abstract":"This contribution aims to describe the methodological approach to Digital Philology by means of the G&A Web Application. It also shows running examples for the: 1) Visualization and ordering of parallel texts subdivided in pericopes; 2) Linguistic annotations; 3) Scholarly comments; and 4)Search functions","keywords":["digital philology","computational philology","software engineering","Greek into Arabic","Computational linguistics"],"pages":"","url":"https:\/\/publications.cnr.it\/doc\/390781","volume":"","doi":"","editors_people":"","editors":[""],"published":"","publisher":"","issn":"","isbn":"","conference_name":"","conference_place":"","conference_date":""},{"id":131965,"last_updated":"2014-11-27 14:59:29","id_people":288551,"institutes":["ILC"],"type":"journal_article","type_order":0,"type_people":"article","title":"Ya\u1e25y\u0101 ibn \u2018Ad\u012b sulla differenza fra la logica greca e la grammatica araba","year":2011,"authors_people":"Nahli, Ouafae","authors_cnr":["Nahli, Ouafae"],"authors_cnr_id":[""],"authors_cnr_institute":["048"],"authors":["Nahli, O."],"abstract":"?is paper examines the Treatise on the Difference between the two fields of philosophical logic and Arabic grammar (Maq?la f? taby?n al-fa?l bayna ?ina'atay al-man?iq al-falsaf? wa-l-na?w al-'arab?) by Ab? Zakariy?' Ya?y? ibn 'Ad?, providing also its Italian translation. It will appear that Ya?y? ibn 'Ad?'s approach is based on F?r?b?'s ideas about the relationship between logic and the sciences of language. Even more important is the fact that the difference established by Ya?y? ibn 'Ad?'s between logic and grammar both as for the subject (maw??') and as for scope (?arad) counts as the source for Avicenna's distinction between subject (maw??') and scope (?arad) of the metaphysics","keywords":[""],"pages":"47-67","url":"http:\/\/www.greekintoarabic.eu\/uploads\/media\/3wafae_utlimo.pdf","volume":"1","doi":"","editors_people":"","editors":[""],"published":"Studia graeco-arabica","publisher":"Pacini Editore (Pisa, Italia)","issn":"2281-2687","isbn":"","conference_name":"","conference_place":"","conference_date":""},{"id":131967,"last_updated":"2014-11-28 13:51:56","id_people":288556,"institutes":["ILC"],"type":"book","type_order":1,"type_people":"book","title":"lingua araba, il sistema verbale","year":2010,"authors_people":"Nahli, Ouafae","authors_cnr":["Nahli, Ouafae"],"authors_cnr_id":[""],"authors_cnr_institute":["048"],"authors":["Nahli, O."],"abstract":"Questo volume offre una descrizione del verbo arabo, in una prospettiva prevalentemente didattica seguendo la struttura di pensiero e le categorie linguistiche proprie della tradizione grammaticale araba. Emerge e si chiarisce cos\u00ec la logica che domina l'articolato sistema verbale arabo e che funge da cardine nell'organizzazione della sintassi e di buona parte della morfologia nominale. Per di pi\u00f9, al termine del libro, \u00e8 presente un capitolo dedicato alla \"frase araba\", ovvero alla \"frase verbale\" e alla \"frase nominale\" ed ai loro rispettivi elementi costitutivi.","keywords":[""],"pages":"140","url":"https:\/\/publications.cnr.it\/doc\/288556","volume":"","doi":"","editors_people":"","editors":[""],"published":"","publisher":"","issn":"","isbn":"9788867413003","conference_name":"","conference_place":"","conference_date":""},{"id":130952,"last_updated":"2014-11-27 13:57:27","id_people":64493,"institutes":["ILC"],"type":"journal_article","type_order":0,"type_people":"article","title":"Risorse monolingui e multilingui. Corpus bilingue italiano-arabo","year":2003,"authors_people":"Picchi E. , Sassolini E. , Nahli O. , Cucurullo S.","authors_cnr":["Cucurullo, Sebastiana","Sassolini, Eva","Nahli, Ouafae","Picchi, Eugenio"],"authors_cnr_id":["16688"],"authors_cnr_institute":[""],"authors":["Picchi, E.","Sassolini, E.","Nahli, O.","Cucurullo, S."],"abstract":"Abstract - The objective of the project is twofold: on the one hand, the creation and elaboration of software procedures for the Arabic language and, on the other hand, the creation of linguistic resources for the management of large Arabic corpora. The linguistic resources are substantially the following: a) Morphological engine for the Arabic language. The engine is constituted by a number of modules: the algorithms and modules for generation and analysis, an appropriate encoding system for the representation of lexical data and of morphological characteristics of Arabic, the so-called \u0093lemmario\u0094, i.e. the archive of lemmas; b) The automatic alignment of parallel texts in Italian and Arabic language; c) Automatic tagging of Arabic texts, performed by using the above morphological engine; d) Systems for accessing and querying (raw and\/or tagged) Arabic texts and parallel Italian-Arabic corpora.","keywords":["Morfologia araba","Corpora bilingui","Analisi testuale","Aligner","Tagger"],"pages":"629-678","url":"https:\/\/publications.cnr.it\/doc\/64493","volume":"18-19","doi":"","editors_people":"","editors":[""],"published":"Linguistica computazionale (Online)","publisher":"Istituti Editoriali e Poligrafici Internazionali (Ghezzano La Fontina, Italia)","issn":"1824-1573","isbn":"","conference_name":"","conference_place":"","conference_date":""},{"id":131968,"last_updated":"2015-08-04 12:31:47","id_people":288585,"institutes":["ILC"],"type":"conference_article","type_order":5,"type_people":"conferenceObject","title":"Italian Arabic Linguistic Tools","year":2002,"authors_people":"Picchi, Eugenio; Sassolini, Eva; Nahli, Ouafae; Cucurullo Sebastiana; Vargas, Isabel Maria","authors_cnr":["Nahli, Ouafae","Sassolini, Eva","Cucurullo, Sebastiana","Picchi, Eugenio"],"authors_cnr_id":["11032","11479","16688"],"authors_cnr_institute":["048","048","048","048"],"authors":["Picchi, E.","Sassolini, E.","Nahli, O.","Cucurullo, S.","Vargas, I. M."],"abstract":"","keywords":[""],"pages":"","url":"https:\/\/publications.cnr.it\/doc\/288585","volume":"Volume II","doi":"","editors_people":"","editors":[""],"published":"Third International Conference on Language Resources and Evaluation","publisher":"","issn":"","isbn":"","conference_name":"LREC 2002","conference_place":"Las Palmas de Gran Canaria, Spain","conference_date":"30th & 31 May 2002"},{"id":131969,"last_updated":"2014-11-27 15:30:17","id_people":288591,"institutes":["ILC"],"type":"technical_report","type_order":8,"type_people":"report","title":"Motore morfologico della lingua araba","year":2002,"authors_people":"Sassolini, Eva; Nahli, Ouafae","authors_cnr":["Nahli, Ouafae","Sassolini, Eva"],"authors_cnr_id":["11032"],"authors_cnr_institute":["048","048"],"authors":["Sassolini, E.","Nahli, O."],"abstract":"","keywords":[""],"pages":"","url":"https:\/\/publications.cnr.it\/doc\/288591","volume":"","doi":"","editors_people":"","editors":[""],"published":"","publisher":"","issn":"","isbn":"","conference_name":"","conference_place":"","conference_date":""}]