{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,21]],"date-time":"2025-12-21T10:04:29Z","timestamp":1766311469149,"version":"3.40.3"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031082764"},{"type":"electronic","value":"9783031082771"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-08277-1_23","type":"book-chapter","created":{"date-parts":[[2022,6,16]],"date-time":"2022-06-16T12:13:01Z","timestamp":1655381581000},"page":"278-290","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["TunBERT: Pretrained Contextualized Text Representation for\u00a0Tunisian Dialect"],"prefix":"10.1007","author":[{"given":"Abir","family":"Messaoudi","sequence":"first","affiliation":[]},{"given":"Ahmed","family":"Cheikhrouhou","sequence":"additional","affiliation":[]},{"given":"Hatem","family":"Haddad","sequence":"additional","affiliation":[]},{"given":"Nourchene","family":"Ferchichi","sequence":"additional","affiliation":[]},{"given":"Moez","family":"BenHajhmida","sequence":"additional","affiliation":[]},{"given":"Abir","family":"Korched","sequence":"additional","affiliation":[]},{"given":"Malek","family":"Naski","sequence":"additional","affiliation":[]},{"given":"Faten","family":"Ghriss","sequence":"additional","affiliation":[]},{"given":"Amine","family":"Kerkeni","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,6,17]]},"reference":[{"key":"23_CR1","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. In: 1st International Conference on Learning Representations, Workshop Track Proceedings (2013)"},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., Zettlemoyer, L.: Deep contextualized word representations. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pp. 2227\u20132237 (2018). https:\/\/www.aclweb.org\/anthology\/N18-1202","DOI":"10.18653\/v1\/N18-1202"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Howard, J., Ruder, S.: Universal language model fine-tuning for text classification. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 328\u2013339 (2018). https:\/\/www.aclweb.org\/anthology\/P18-1031","DOI":"10.18653\/v1\/P18-1031"},{"key":"23_CR4","unstructured":"Bahdanau, D., Cho, K., Bengio,Y.: Neural machine translation by jointly learning to align and translate. In: Proceedings of the 3rd International Conference on Learning Representations (2015)"},{"key":"23_CR5","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30, 5998\u20136008 (2017). http:\/\/papers.nips.cc\/paper\/7181-attention-is-all-you-need.pdf"},{"key":"23_CR6","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long And Short Papers), pp. 4171\u20134186 (2019)"},{"key":"23_CR7","unstructured":"Antoun, W., Baly, F., Hajj, H.: AraBERT: transformer-based model for Arabic language understanding. In: Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection, pp. 9\u201315 (2020)"},{"key":"23_CR8","unstructured":"Wuwei, L., Yang, C., Wei, X., Alan, R.: GigaBERT: zero-shot transfer learning from English to Arabic. In: Proceedings of the 2020 Conference on Empirical Methods on Natural Language Processing (EMNLP) (2020)"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Pires, T., Schlinger, E., Garrette, D.: How multilingual is multilingual BERT? In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 4996\u20135001 (2019). https:\/\/www.aclweb.org\/anthology\/P19-1493","DOI":"10.18653\/v1\/P19-1493"},{"key":"23_CR10","unstructured":"Fourati, C., Messaoudi, A., Haddad, H.: TUNIZI: a Tunisian Arabizi sentiment analysis dataset. In: AfricaNLP Workshop, Putting Africa on the NLP Map. ICLR 2020, Virtual Event. arXiv:3091079 (2020)"},{"key":"23_CR11","unstructured":"Delobelle, P., et al.: Computing research repository. arXiv:1907.11692 (2019)"},{"key":"23_CR12","unstructured":"Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: ALBERT: a lite BERT for self-supervised learning of language representations. In: Proceedings of the 8th International Conference on Learning Representations (ICLR) (2020)"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.: GloVe: Global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"23_CR14","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1162\/tacl_a_00051","volume":"5","author":"P Bojanowski","year":"2017","unstructured":"Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. Trans. Assoc. Comput. Linguist. 5, 135\u2013146 (2017)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"23_CR15","unstructured":"Conneau, A., Lample, G.: Cross-lingual language model pretraining. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 7059\u20137069 (2019)"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Delobelle, P., Winters, T., Berendt, B.: RobBERT: a dutch RoBERTa-based language model. Computing Research Repository, version 2. arXiv:2001.06286 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.292"},{"key":"23_CR17","unstructured":"Le, H., et al.: FlauBERT: unsupervised language model pre-training for French. In: Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC), pp. 2479\u20132490 (2020)"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Martin, L., et al.: CamemBERT: a tasty French language model. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 7203\u20137219 (2020)","DOI":"10.18653\/v1\/2020.acl-main.645"},{"key":"23_CR19","unstructured":"Canete, J., Chaperon, G., Fuentes, R., Ho, J., Kang, H., P\u00e9rez, J.: Spanish pre-trained BERT model and evaluation data. In: PML4DC @ ICLR 2020, p. 2020 (2020)"},{"key":"23_CR20","unstructured":"Virtanen, A., et al.: Multilingual is not enough: BERT for finnish. Computing Research Repository, version 1. arXiv:1912.07076 (2019)"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Medhaffar, S., Bougares, F., Est\u00e8ve, Y., Hadrich-Belguith, L.: Sentiment analysis of Tunisian dialects: linguistic resources and experiments. In: Proceedings of the Third Arabic Natural Language Processing Workshop, pp. 55\u201361 (2017)","DOI":"10.18653\/v1\/W17-1307"},{"key":"23_CR22","unstructured":"Sayadi, K., Liwicki, M., Ingold, R., Bui, M.: Tunisian dialect and modern standard Arabic dataset for sentiment analysis: Tunisian election context. In: Proceedings of the Second International Conference on Arabic Computational Linguistics, ACLING, pp. 35\u201353 (2016)"},{"key":"23_CR23","unstructured":"Zaidan, O., Callison-Burch, C.: The Arabic online commentary dataset: an annotated dataset of informal Arabic with high dialectal content. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pp. 37\u201341 (2011)"},{"key":"23_CR24","unstructured":"El-Haj, M., Rayson, P., Aboelezz, M.: Arabic dialect identification in the context of bivalency and code-switching. In: Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC), pp. 3622\u20133627 (2018)"},{"key":"23_CR25","unstructured":"Harrat, S., Meftouh, K., Sma\u00efli, K.: Maghrebi Arabic dialect processing: an overview. J. Int. Sci. Gen. Appl. 1 (2018)"},{"key":"23_CR26","unstructured":"Horesh, S.: Languages of the Middle East and North Africa. In: The SAGE Encyclopedia of Human Communication Sciences and Disorders, vol. 1, pp. 1058\u20131061 (2019)"},{"key":"23_CR27","unstructured":"Bouamor, H., et al.: The MADAR Arabic dialect corpus and lexicon. In: The International Conference on Language Resources and Evaluation (2018)"},{"key":"23_CR28","doi-asserted-by":"crossref","unstructured":"Bouamor, H., Hassan, S., Habash, N.: The MADAR shared task on Arabic fine-grained dialect identification. In: Proceedings of the Fourth Arabic Natural Language Processing Workshop, pp. 199\u2013207 (2019)","DOI":"10.18653\/v1\/W19-4622"},{"key":"23_CR29","doi-asserted-by":"crossref","unstructured":"Mozannar, H., Maamary, E., El Hajal, K., Hajj, H.: Neural Arabic question answering. In: Proceedings of the Fourth Arabic Natural Language Processing Workshop, pp. 108\u2013118 (2019). https:\/\/www.aclweb.org\/anthology\/W19-4612","DOI":"10.18653\/v1\/W19-4612"},{"key":"23_CR30","doi-asserted-by":"crossref","unstructured":"Chen, D., Fisch, A., Weston, J., Bordes, A.: Reading Wikipedia to answer open-domain questions. ArXiv. abs\/1704.00051 (2017)","DOI":"10.18653\/v1\/P17-1171"},{"key":"23_CR31","first-page":"1","volume":"27","author":"H Mulki","year":"2020","unstructured":"Mulki, H., Haddad, H., Gridach, M., Babao\u011flu, I.: Syntax-ignorant N-gram embeddings for dialectal Arabic sentiment analysis. Nat. Lang. Eng. 27, 1\u201324 (2020)","journal-title":"Nat. Lang. Eng."}],"container-title":["Communications in Computer and Information Science","Intelligent Systems and Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-08277-1_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,16]],"date-time":"2022-06-16T12:18:54Z","timestamp":1655381934000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-08277-1_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031082764","9783031082771"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-08277-1_23","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"17 June 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Systems and Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hammamet","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tunisia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 March 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 March 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ispr22022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ispr2022.sciencesconf.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"91","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"22","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"10","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"24% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Due to the COVID-19 pandemic the conference was held online.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}