{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T22:29:29Z","timestamp":1742941769720,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030923068"},{"type":"electronic","value":"9783030923075"}],"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\/978-3-030-92307-5_44","type":"book-chapter","created":{"date-parts":[[2021,12,6]],"date-time":"2021-12-06T14:04:20Z","timestamp":1638799460000},"page":"379-386","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Better Multiway Attention Framework for\u00a0Fine-Tuning"],"prefix":"10.1007","author":[{"given":"Kaifeng","family":"Hao","sequence":"first","affiliation":[]},{"given":"Jianfeng","family":"Li","sequence":"additional","affiliation":[]},{"given":"Cuiqin","family":"Hou","sequence":"additional","affiliation":[]},{"given":"Pengyu","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,12,2]]},"reference":[{"key":"44_CR1","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding (2018)"},{"key":"44_CR2","unstructured":"Yang, Z., Dai, Z., et al.: XLNet: generalized autoregressive pretraining for language understanding. In: NeurIPS (2019)"},{"key":"44_CR3","unstructured":"Liu, Y., Ott, M., et al.: Roberta: a robustly optimized BERT pretraining approach (2019). arXiv preprint arXiv:1907.11692"},{"key":"44_CR4","unstructured":"Lan, Z., Chen, M., et al.: Albert: a lite bert for self-supervised learning of language representations (2019)"},{"key":"44_CR5","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks. In: EMNLP-IJCNLP, pp. 2982\u20133992 (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"44_CR6","doi-asserted-by":"crossref","unstructured":"Jawahar, G., Sagot, B., Seddah, D.: What does BERT learn about the structure of language? In: ACL, pp. 3651\u20133657 (2019)","DOI":"10.18653\/v1\/P19-1356"},{"key":"44_CR7","unstructured":"Vaswani, A., Shazeer, N., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"44_CR8","doi-asserted-by":"crossref","unstructured":"Tan, C., Wei, F., et al.: Multiway attention networks for modeling sentence pairs. In: IJCAI, pp. 4411\u20134417 (2018)","DOI":"10.24963\/ijcai.2018\/613"},{"key":"44_CR9","doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., et al.: Glue: a multi-task benchmark and analysis platform for natural language understanding (2018). arXiv preprint arXiv:1804.07461","DOI":"10.18653\/v1\/W18-5446"},{"key":"44_CR10","doi-asserted-by":"crossref","unstructured":"Rajpurkar, P., Jia, R., Liang, P.: Know what you don\u2019t know: unanswerable questions for SQuAD. In: ACL, pp. 784\u2013789 (2018)","DOI":"10.18653\/v1\/P18-2124"},{"key":"44_CR11","doi-asserted-by":"crossref","unstructured":"Lai, G., Xie, Q., et al.: RACE: large-scale reading comprehension dataset from examinations. In: EMNLP, pp. 785\u2013794 (2017)","DOI":"10.18653\/v1\/D17-1082"},{"key":"44_CR12","doi-asserted-by":"crossref","unstructured":"Liu, X., He, P., Chen, W., Gao, J.: Multi-task deep neural networks for natural language understanding. In: ACL (2019)","DOI":"10.18653\/v1\/P19-1441"},{"key":"44_CR13","doi-asserted-by":"crossref","unstructured":"Sun, Y., Wang, S., Li, Y.K., Feng, S.: ERNIE 2.0: a continual pre-training framework for language understanding. AAAI 34(05), 8968\u20138975 (2019)","DOI":"10.1609\/aaai.v34i05.6428"},{"key":"44_CR14","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1007\/978-3-030-32381-3_16","volume-title":"Chinese Computational Linguistics","author":"C Sun","year":"2019","unstructured":"Sun, C., Qiu, X., Xu, Y., Huang, X.: How to fine-tune BERT for text classification? In: Sun, M., Huang, X., Ji, H., Liu, Z., Liu, Y. (eds.) CCL 2019. LNCS (LNAI), vol. 11856, pp. 194\u2013206. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-32381-3_16"},{"key":"44_CR15","doi-asserted-by":"crossref","unstructured":"Xu, H., Zhang, L., et al.: Curriculum learning for natural language understanding. In: ACL, pp. 6095\u20136104 (2020)","DOI":"10.18653\/v1\/2020.acl-main.542"},{"key":"44_CR16","doi-asserted-by":"crossref","unstructured":"Peinelt, N., Nguyen, D., Liakata, M.: tBERT: topic models and BERT joining forces for semantic similarity detection. In: ACL, pp. 7047\u20137055 (2020)","DOI":"10.18653\/v1\/2020.acl-main.630"},{"key":"44_CR17","doi-asserted-by":"crossref","unstructured":"Luong, T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. In: EMNLP, pp. 1412\u20131421 (2015)","DOI":"10.18653\/v1\/D15-1166"},{"key":"44_CR18","unstructured":"Kim, J.-H., Jun, J., Zhang, B.T.: Bilinear attention networks. In: NIPS (2018)"},{"key":"44_CR19","unstructured":"Gong, L., He, D., et al.: Efficient training of BERT by progressively stacking, pp. 2337\u20132346 (2019)"},{"key":"44_CR20","unstructured":"Ta-Chun, S., Cheng, H.-C.: Attention for anywhere. DSAA, SesameBERT (2020)"},{"key":"44_CR21","doi-asserted-by":"publisher","first-page":"101164","DOI":"10.1016\/j.csl.2020.101164","volume":"66","author":"Y Arase","year":"2021","unstructured":"Arase, Y., Tsujii, J.: Transfer fine-tuning of BERT with phrasal paraphrases. Comput. Speech Lang. 66, 101164 (2021)","journal-title":"Comput. Speech Lang."}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-92307-5_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,6]],"date-time":"2021-12-06T14:34:29Z","timestamp":1638801269000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-92307-5_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030923068","9783030923075"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-92307-5_44","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"2 December 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sanur, Bali","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Indonesia","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":"8 December 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2021.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-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":"1093","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":"226","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":"177","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":"21% - 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":"2.57","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":"6","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)"}}]}}