{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:27:40Z","timestamp":1770917260761,"version":"3.50.1"},"reference-count":64,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Key Projects of National Natural Science Foundation of China","award":["U1836222 and 61733011"],"award-info":[{"award-number":["U1836222 and 61733011"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Asian Low-Resour. Lang. Inf. Process."],"published-print":{"date-parts":[[2022,5,31]]},"abstract":"<jats:p>Implicit discourse relation recognition is a challenging task due to the absence of the necessary informative clues from explicit connectives. An implicit discourse relation recognizer has to carefully tackle the semantic similarity of sentence pairs and the severe data sparsity issue. In this article, we learn token embeddings to encode the structure of a sentence from a dependency point of view in their representations and use them to initialize a baseline model to make it really strong. Then, we propose a novel memory component to tackle the data sparsity issue by allowing the model to master the entire training set, which helps in achieving further performance improvement. The memory mechanism adequately memorizes information by pairing representations and discourse relations of all training instances, thus filling the slot of the data-hungry issue in the current implicit discourse relation recognizer. The proposed memory component, if attached with any suitable baseline, can help in performance enhancement. The experiments show that our full model with memorizing the entire training data provides excellent results on PDTB and CDTB datasets, outperforming the baselines by a fair margin.<\/jats:p>","DOI":"10.1145\/3485016","type":"journal-article","created":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T14:36:25Z","timestamp":1639406185000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Memorizing All for Implicit Discourse Relation Recognition"],"prefix":"10.1145","volume":"21","author":[{"given":"Kashif","family":"Munir","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering; Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering; MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongxiao","family":"Bai","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering; Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering; MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hai","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering; Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering; MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junhan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Computer Graphics Technology, Purdue University, Indiana, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,12,13]]},"reference":[{"key":"e_1_3_1_2_1","first-page":"571","volume-title":"Proceedings of the 27th International Conference on Computational Linguistics (COLING\u201918)","author":"Bai Hongxiao","year":"2018","unstructured":"Hongxiao Bai and Hai Zhao. 2018. Deep enhanced representation for implicit discourse relation recognition. In Proceedings of the 27th International Conference on Computational Linguistics (COLING\u201918). 571\u2013583."},{"key":"e_1_3_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1262"},{"key":"e_1_3_1_4_1","first-page":"2753","volume-title":"Proceedings of the 27th International Conference on Computational Linguistics (COLING\u201918)","author":"Cai Jiaxun","year":"2018","unstructured":"Jiaxun Cai, Shexia He, Zuchao Li, and Hai Zhao. 2018. A full end-to-end semantic role labeler, syntactic-agnostic over syntactic-aware? In Proceedings of the 27th International Conference on Computational Linguistics (COLING\u201918). 2753\u20132765."},{"key":"e_1_3_1_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/3016100.3016311"},{"key":"e_1_3_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1163"},{"key":"e_1_3_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1013"},{"key":"e_1_3_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1191"},{"key":"e_1_3_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/3305381.3305478"},{"key":"e_1_3_1_10_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR\u201917)","author":"Dozat Timothy","year":"2017","unstructured":"Timothy Dozat and Christopher D. Manning. 2017. Deep biaffine attention for neural dependency parsing. In Proceedings of the International Conference on Learning Representations (ICLR\u201917)."},{"key":"e_1_3_1_11_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1168"},{"key":"e_1_3_1_12_1","first-page":"547","volume-title":"Proceedings of the 27th International Conference on Computational Linguistics (COLING\u201918)","author":"Guo Fengyu","year":"2018","unstructured":"Fengyu Guo, Ruifang He, Di Jin, Jianwu Dang, Longbiao Wang, and Xiangang Li. 2018. Implicit discourse relation recognition using neural tensor network with interactive attention and sparse learning. In Proceedings of the 27th International Conference on Computational Linguistics (COLING\u201918). 547\u2013558."},{"key":"e_1_3_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1192"},{"key":"e_1_3_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1162"},{"key":"e_1_3_1_15_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1092"},{"key":"e_1_3_1_16_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00142"},{"key":"e_1_3_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1037"},{"key":"e_1_3_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2070"},{"key":"e_1_3_1_19_1","first-page":"584","volume-title":"Proceedings of the 27th International Conference on Computational Linguistics (COLING\u201918)","author":"Kishimoto Yudai","year":"2018","unstructured":"Yudai Kishimoto, Yugo Murawaki, and Sadao Kurohashi. 2018. A knowledge-augmented neural network model for implicit discourse relation classification. In Proceedings of the 27th International Conference on Computational Linguistics (COLING\u201918). 584\u2013595."},{"key":"e_1_3_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045536"},{"key":"e_1_3_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1134"},{"key":"e_1_3_1_22_1","doi-asserted-by":"publisher","DOI":"10.5555\/3171837.3171848"},{"key":"e_1_3_1_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/3504035.3504629"},{"key":"e_1_3_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030500"},{"key":"e_1_3_1_25_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016730"},{"key":"e_1_3_1_26_1","doi-asserted-by":"publisher","DOI":"10.5555\/1699510.1699555"},{"key":"e_1_3_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1050"},{"key":"e_1_3_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1130"},{"key":"e_1_3_1_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/3016100.3016286"},{"key":"e_1_3_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-2020"},{"key":"e_1_3_1_31_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295377"},{"key":"e_1_3_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1147"},{"key":"e_1_3_1_33_1","first-page":"142","volume-title":"Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL:HLT\u201916)","author":"Mrk\u0161i\u0107 Nikola","year":"2016","unstructured":"Nikola Mrk\u0161i\u0107, Diarmuid \u00d3. S\u00e9aghdha, Blaise Thomson, Milica Ga\u0161i\u0107, Lina M. Rojas-Barahona, Pei-Hao Su, David Vandyke, Tsung-Hsien Wen, and Steve Young. 2016a. Counter-fitting word vectors to linguistic constraints. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL:HLT\u201916). 142\u2013148."},{"key":"e_1_3_1_34_1","volume-title":"Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL: HLT\u201916)","author":"Mrk\u0161i\u0107 Nikola","year":"2016","unstructured":"Nikola Mrk\u0161i\u0107, Diarmuid O. S\u00e9aghdha, Blaise Thomson, Milica Ga\u0161i\u0107, Lina Rojas-Barahona, Pei-Hao Su, David Vandyke, Tsung-Hsien Wen, and Steve Young. 2016b. Counter-fitting word vectors to linguistic constraints. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL: HLT\u201916)."},{"key":"e_1_3_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3096041"},{"key":"e_1_3_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1442"},{"key":"e_1_3_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1161"},{"key":"e_1_3_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"e_1_3_1_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/1690219.1690241"},{"key":"e_1_3_1_40_1","volume-title":"Proceedings of the 32nd International Flairs Conference","author":"Popa Diana Nicoleta","year":"2019","unstructured":"Diana Nicoleta Popa, Julien Perez, James Henderson, and Eric Gaussier. 2019. Implicit discourse relation classification with syntax-aware contextualized word representations. In Proceedings of the 32nd International Flairs Conference."},{"key":"e_1_3_1_41_1","first-page":"2961","volume-title":"Proceedings of the 6th conference on International Language Resources and Evaluation (LREC\u201908)","author":"Prasad Rashmi","year":"2008","unstructured":"Rashmi Prasad, Nikhil Dinesh, Alan Lee, Eleni Miltsakaki, Livio Robaldo, Aravind K. Joshi, and Bonnie L. Webber. 2008. The Penn Discourse TreeBank 2.0. In Proceedings of the 6th conference on International Language Resources and Evaluation (LREC\u201908). 2961\u20132968."},{"key":"e_1_3_1_42_1","first-page":"1914","volume-title":"Proceedings of the 26th International Conference on Computational Linguistics (COLING\u201916)","author":"Qin Lianhui","year":"2016","unstructured":"Lianhui Qin, Zhisong Zhang, and Hai Zhao. 2016a. Implicit discourse relation recognition with context-aware character-enhanced embeddings. In Proceedings of the 26th International Conference on Computational Linguistics (COLING\u201916). 1914\u20131924."},{"key":"e_1_3_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-2010"},{"key":"e_1_3_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1246"},{"key":"e_1_3_1_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1093"},{"key":"e_1_3_1_46_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2040"},{"key":"e_1_3_1_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-1027"},{"key":"e_1_3_1_48_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1081"},{"key":"e_1_3_1_49_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-2007"},{"key":"e_1_3_1_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2088"},{"key":"e_1_3_1_51_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-2005"},{"key":"e_1_3_1_52_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"e_1_3_1_53_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-0416"},{"key":"e_1_3_1_54_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969442.2969505"},{"key":"e_1_3_1_55_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969442.2969512"},{"key":"e_1_3_1_56_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-2632"},{"key":"e_1_3_1_57_1","first-page":"4201","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL\u201919)","author":"Ngo Linh Van","year":"2019","unstructured":"Linh Van Ngo, Khoat Than, Thien Huu Nguyen, et\u00a0al. 2019. Employing the correspondence of relations and connectives to identify implicit discourse relations via label embeddings. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL\u201919). 4201\u20134207."},{"key":"e_1_3_1_58_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR\u201915)","author":"Weston Jason","year":"2015","unstructured":"Jason Weston, Sumit Chopra, and Antoine Bordes. 2015. Memory networks. In Proceedings of the International Conference on Learning Representations (ICLR\u201915)."},{"key":"e_1_3_1_59_1","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045643"},{"key":"e_1_3_1_60_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1079"},{"key":"e_1_3_1_61_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K15-2001"},{"key":"e_1_3_1_62_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-2001"},{"key":"e_1_3_1_63_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1266"},{"key":"e_1_3_1_64_1","unstructured":"Yingxue Zhang Ping Jian Fandong Meng Ruiying Geng Wei Cheng and Jie Zhou. 2019. Semantic graph convolutional network for implicit discourse relation classification. Retrieved from https:\/\/arxiv.org\/abs\/1910.09183."},{"key":"e_1_3_1_65_1","doi-asserted-by":"publisher","DOI":"10.5555\/2390524.2390535"}],"container-title":["ACM Transactions on Asian and Low-Resource Language Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3485016","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3485016","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:17:15Z","timestamp":1750191435000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3485016"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":64,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,5,31]]}},"alternative-id":["10.1145\/3485016"],"URL":"https:\/\/doi.org\/10.1145\/3485016","relation":{},"ISSN":["2375-4699","2375-4702"],"issn-type":[{"value":"2375-4699","type":"print"},{"value":"2375-4702","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,13]]},"assertion":[{"value":"2021-05-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-09-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-12-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}