{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:14:04Z","timestamp":1742912044526,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030884796"},{"type":"electronic","value":"9783030884802"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-88480-2_17","type":"book-chapter","created":{"date-parts":[[2021,10,11]],"date-time":"2021-10-11T11:04:52Z","timestamp":1633950292000},"page":"210-223","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Pre-trained Language Models for Tagalog with Multi-source Data"],"prefix":"10.1007","author":[{"given":"Shengyi","family":"Jiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingwen","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaotian","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nankai","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,10,6]]},"reference":[{"key":"17_CR1","unstructured":"Devlin, J., Chang, M.W., Lee K., Toutanova K.: BERT: pre-training of deep bidirectional transformers for language understanding, In: Proceedings of NAACLHLT 2019, pp. 4171\u20134186 (2019)"},{"key":"17_CR2","unstructured":"Cui, Y., Che, W., Liu, T., Qin, B., Yang, Z., Wang, S., Hu, G.: Pre-training with whole word masking for Chinese BERT. CORR (2019)"},{"key":"17_CR3","unstructured":"de Vries, W., van Cranenburgh, A., Bisazza, A., Caselli, T., van Noord, G., Nissim, M.: BERTje: a Dutch BERT model. CORR (2019)"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Vu, X.S., Vu, T., Tran, S.N., Jiang, L.: ETNLP: a visual-aided systematic approach to select pre-trained embeddings for a downstream task. In: Proceedings of the International Conference on Recent Advances in Natural Language Processing, pp. 1285\u20131294 (2019)","DOI":"10.26615\/978-954-452-056-4_147"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Martin, L., et al.: CamemBERT: a tasty French language model. In: Annual Meeting of the Association for Computational Linguistics, pp. 7203\u20137219 (2020)","DOI":"10.18653\/v1\/2020.acl-main.645"},{"key":"17_CR6","unstructured":"Lample, G., Conneau A.: Cross-lingual language model pretraining. CORR (2019)"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Conneau, A., et al.: Unsupervised cross-lingual representation learning at scale. In: Annual Meeting of the Association for Computational Linguistics, pp. 8440\u20138451 (2020)","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"17_CR8","unstructured":"Cruz, J.C.B., Cheng, C.: Evaluating language model finetuning techniques for low-resource languages. CORR (2019)"},{"key":"17_CR9","unstructured":"Cruz, J.C.B., Cheng, C.: Establishing baselines for text classification in low-resource languages. CORR (2020)"},{"key":"17_CR10","unstructured":"Cruz, J.C.B., Resabal, J.K., Lin, J., Velasco, D. J., Cheng, C.: Investigating the true performance of transformers in low-resource languages: A case study in automatic corpus creation. CORR (2020)"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Xue, L., et al.: mT5: a massively multilingual pre-trained text-to-text transformer. CORR (2021)","DOI":"10.18653\/v1\/2021.naacl-main.41"},{"key":"17_CR12","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. CORR (2019)"},{"key":"17_CR13","unstructured":"Cheng, C., Rabo, S.: TPOST: a template-based, n-gram part-of-speech tagger for Tagalog. J. Res. Sci. Comput. Eng. 3(1) (2004)"},{"key":"17_CR14","unstructured":"Reyes, C.D.E., Suba, K.R.S., Razon, A.R., Naval Jr., P.C.: SVPOSTA part-of-speech tagger for Tagalog using support vector machines. In: Proceedings of the 11th Philippine Computing Science Congress (2011)"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Olivo, J.F.T., Hari, P.J.T., dela Fuente, M.B.: CRFPOST: part-of-speech tagger for Filipino texts using conditional random fields. In: Proceedings of the 2nd International Conference on Algorithms, Computing and Artificial Intelligence, pp. 444\u2013449 (2019)","DOI":"10.1145\/3377713.3377788"},{"key":"17_CR16","unstructured":"Clark, K., Luong, M.T., Le, Q.V., Manning, C.D.: ELECTRA: pre-training text encoders as discriminators rather than generator. In: Proceedings of International Conference on Learning Representations (2020)"},{"key":"17_CR17","unstructured":"Vaswani, A., et al. Attention is all you need. CORR (2017)"},{"key":"17_CR18","unstructured":"Su\u00e1rez, P.O., Romary, L., Sagot, B.: A monolingual approach to contextualized word embeddings for mid-resource languages. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (2020)"},{"key":"17_CR19","unstructured":"Grave, E., Bojanowski, P., Gupta, P., Joulin, A., ikolov, T.: Learning word vectors for 157 languages. In: Proceedings of the 11th Language Resources and Evaluation Conference, European Language Resource Association (2018)"},{"key":"17_CR20","unstructured":"Wu, Y., Schuster, M., Chen, Z., Le, Q.V., Norouzi, M., Macherey, W., et al.: Google's neural machine translation system: bridging the gap between human and machine translation. CORR (2016)"},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. CORR (2015)","DOI":"10.18653\/v1\/P16-1162"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-88480-2_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T15:43:00Z","timestamp":1709826180000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-88480-2_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030884796","9783030884802"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-88480-2_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"6 October 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Qingdao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 October 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2021\/","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":"Softconf","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"446","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":"66","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":"0","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":"15% - 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":"1.5","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"23 poster papers and 27 workshop papers are also included.","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)"}}]}}