{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T16:21:52Z","timestamp":1742919712521,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031446924"},{"type":"electronic","value":"9783031446931"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-44693-1_5","type":"book-chapter","created":{"date-parts":[[2023,10,7]],"date-time":"2023-10-07T08:02:39Z","timestamp":1696665759000},"page":"57-68","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Recurrent Transformers for\u00a0Long Document Understanding"],"prefix":"10.1007","author":[{"given":"Chuzhan","family":"Hao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minghui","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongming","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,10,8]]},"reference":[{"key":"5_CR1","unstructured":"Devlin, J., Chang, M.-W., 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, Minneapolis, Minnesota, June 2019, pp. 4171\u20134186. Association for Computational Linguistics (2019)"},{"key":"5_CR2","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized BERT pretraining approach, arXiv preprint arXiv:1907.11692 (2019)"},{"key":"5_CR3","unstructured":"Hutchins, D., Schlag, I., Wu, Y., Dyer, E., Neyshabur, B.: Block-recurrent transformers, arXiv preprint arXiv:2203.07852 (2022)"},{"key":"5_CR4","unstructured":"Ding, M., Zhou, C., Yang, H., Tang, J.: CogLTX: applying BERT to long texts. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 12 792\u201312 804. Curran Associates Inc (2020)"},{"key":"5_CR5","unstructured":"Beltagy, I., Peters, M.E., Cohan, A.: Longformer: the long-document transformer, arXiv preprint arXiv:2004.05150 (2020)"},{"key":"5_CR6","unstructured":"Kitaev, N., Kaiser, L., Levskaya, A.: Reformer: the efficient transformer. In: International Conference on Learning Representations (2020)"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Fiok, K., et al.: Text guide: improving the quality of long text classification by a text selection method based on feature importance. IEEE Access 9, 105 439\u2013105 450 (2021)","DOI":"10.1109\/ACCESS.2021.3099758"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q., Salakhutdinov, R.: Transformer-XL: attentive language models beyond a fixed-length context. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Florence, Italy, July 2019, pp. 2978\u20132988. Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/P19-1285"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Pappagari, R., \u017belasko, P., Villalba, J., Carmiel, Y., Dehak, N.: Hierarchical transformers for long document classification. In: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 838\u2013844 (2019)","DOI":"10.1109\/ASRU46091.2019.9003958"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Gong, H., Shen, Y., Yu, D., Chen, J., Yu, D.: Recurrent chunking mechanisms for long-text machine reading comprehension. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, July 2020. Online, pp. 6751\u20136761 (2020)","DOI":"10.18653\/v1\/2020.acl-main.603"},{"key":"5_CR11","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1162\/tacl_a_00353","volume":"9","author":"A Roy","year":"2021","unstructured":"Roy, A., Saffar, M., Vaswani, A., Grangier, D.: Efficient content-based sparse attention with routing transformers. Trans. Assoc. Comput. Linguist. 9, 53\u201368 (2021)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"5_CR12","unstructured":"Rae, J.W., Potapenko, A., Jayakumar, S.M., Hillier, C., Lillicrap, T.P.: Compressive transformers for long-range sequence modelling. In: International Conference on Learning Representations (2020)"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Park, H.H., Vyas, Y., Shah, K.: Efficient classification of long documents using transformers, arXiv preprint arXiv:2203.11258 (2022)","DOI":"10.18653\/v1\/2022.acl-short.79"},{"key":"5_CR14","unstructured":"Zaheer, M., et al.: Big bird: transformers for longer sequences. In: Advances in Neural Information Processing Systems, vol. 33, pp. 17 283\u201317 297 (2020)"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Wang, N., et al.: ClusterFormer: neural clustering attention for efficient and effective transformer. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, Dublin, Ireland, May 2022, pp. 2390\u20132402. Association for Computational Linguistics (2022)","DOI":"10.18653\/v1\/2022.acl-long.170"},{"key":"5_CR16","unstructured":"Wang, S., Li, B.Z., Khabsa, M., Fang, H., Ma, H.: Linformer: self-attention with linear complexity, arXiv preprint arXiv:2006.04768 (2020)"},{"key":"5_CR17","first-page":"4271","volume":"33","author":"Z Dai","year":"2020","unstructured":"Dai, Z., Lai, G., Yang, Y., Le, Q.: Funnel-transformer: filtering out sequential redundancy for efficient language processing. Adv. Neural. Inf. Process. Syst. 33, 4271\u20134282 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Wu, C., Wu, F., Qi, T., Huang, Y.: Hi-transformer: hierarchical interactive transformer for efficient and effective long document modeling. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, pp. 848\u2013853. Online: Association for Computational Linguistics, August 2021","DOI":"10.18653\/v1\/2021.acl-short.107"},{"key":"5_CR19","unstructured":"Su, J., Lu, Y., Pan, S., Wen, B., Liu, Y.: Roformer: enhanced transformer with rotary position embedding (2021)"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar, October 2014, pp. 1724\u20131734. Association for Computational Linguistics (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"5_CR21","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Kiesel, J., et al.: SemEval-2019 task 4: hyperpartisan news detection. In: Proceedings of the 13th International Workshop on Semantic Evaluation, Minneapolis, Minnesota, USA, June 2019, pp. 829\u2013839. Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/S19-2145"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Lang, K.: NewsWeeder: learning to filter netnews. In: Machine Learning Proceedings, pp. 331\u2013339. Elsevier (1995)","DOI":"10.1016\/B978-1-55860-377-6.50048-7"},{"key":"5_CR24","doi-asserted-by":"crossref","unstructured":"Diao, Q., Qiu, M., Wu, C.-Y., Smola, A.J., Jiang, J., Wang, C.: Jointly modeling aspects, ratings and sentiments for movie recommendation (JMARS). In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 193\u2013202 (2014)","DOI":"10.1145\/2623330.2623758"},{"key":"5_CR25","unstructured":"Bamman, D., Smith, N.A.: New alignment methods for discriminative book summarization, arXiv preprint arXiv:1305.1319 (2013)"},{"key":"5_CR26","doi-asserted-by":"crossref","unstructured":"Chalkidis, I., Fergadiotis, E., Malakasiotis, P., Androutsopoulos, I.: Large-scale multi-label text classification on EU legislation. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy, July 2019, pp. 6314\u20136322. Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/P19-1636"}],"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\/978-3-031-44693-1_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,9]],"date-time":"2023-10-09T08:18:00Z","timestamp":1696839480000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44693-1_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031446924","9783031446931"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44693-1_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"8 October 2023","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":"Foshan","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2023\/index.php","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":"478","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":"143","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":"30% - 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":"4","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)"}}]}}