{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T11:46:42Z","timestamp":1742644002932},"reference-count":81,"publisher":"MIT Press - Journals","license":[{"start":{"date-parts":[[2022,2,11]],"date-time":"2022-02-11T00:00:00Z","timestamp":1644537600000},"content-version":"vor","delay-in-days":41,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,2,9]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Discourse parsing has been studied for decades. However, it still remains challenging to utilize discourse parsing for real-world applications because the parsing accuracy degrades significantly on out-of-domain text. In this paper, we report and discuss the effectiveness and limitations of bootstrapping methods for adapting modern BERT-based discourse dependency parsers to out-of-domain text without relying on additional human supervision. Specifically, we investigate self-training, co-training, tri-training, and asymmetric tri-training of graph-based and transition-based discourse dependency parsing models, as well as confidence measures and sample selection criteria in two adaptation scenarios: monologue adaptation between scientific disciplines and dialogue genre adaptation. We also release COVID-19 Discourse Dependency Treebank (COVID19-DTB), a new manually annotated resource for discourse dependency parsing of biomedical paper abstracts. The experimental results show that bootstrapping is significantly and consistently effective for unsupervised domain adaptation of discourse dependency parsing, but the low coverage of accurately predicted pseudo labels is a bottleneck for further improvement. We show that active learning can mitigate this limitation.<\/jats:p>","DOI":"10.1162\/tacl_a_00451","type":"journal-article","created":{"date-parts":[[2022,2,11]],"date-time":"2022-02-11T16:36:50Z","timestamp":1644597410000},"page":"127-144","update-policy":"http:\/\/dx.doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":1,"title":["Out-of-Domain Discourse Dependency Parsing via Bootstrapping: An Empirical Analysis on Its Effectiveness and Limitation"],"prefix":"10.1162","volume":"10","author":[{"given":"Noriki","family":"Nishida","sequence":"first","affiliation":[{"name":"RIKEN Center for Advanced Intelligence Project, Japan. noriki.nishida@riken.jp"}]},{"given":"Yuji","family":"Matsumoto","sequence":"additional","affiliation":[{"name":"RIKEN Center for Advanced Intelligence Project, Japan. yuji.matsumoto@riken.jp"}]}],"member":"281","published-online":{"date-parts":[[2022,2,9]]},"reference":[{"key":"2022033118510842800_bib1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073143","article-title":"Bootstrapping","volume-title":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Abney","year":"2002"},{"key":"2022033118510842800_bib2","doi-asserted-by":"publisher","first-page":"928","DOI":"10.18653\/v1\/D15-1109","article-title":"Discourse parsing for multi-party chat dialogues","volume-title":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Afantenos","year":"2015"},{"key":"2022033118510842800_bib3","first-page":"2721","article-title":"Discourse structure and dialogue acts in multiparty dialogue: the STAC corpus","volume-title":"Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC)","author":"Asher","year":"2016"},{"key":"2022033118510842800_bib4","volume-title":"Logics of Conversation","author":"Asher","year":"2003"},{"key":"2022033118510842800_bib5","doi-asserted-by":"publisher","first-page":"640","DOI":"10.18653\/v1\/P19-1061","article-title":"Data programming for learning discourse structure","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Badene","year":"2019"},{"key":"2022033118510842800_bib6","doi-asserted-by":"publisher","first-page":"2296","DOI":"10.18653\/v1\/D19-1234","article-title":"Weak supervision for learning discourse structure","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"Badene","year":"2019"},{"key":"2022033118510842800_bib7","doi-asserted-by":"publisher","first-page":"3615","DOI":"10.18653\/v1\/D19-1371","article-title":"SciBERT: A pretrained language model for scientific text","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"Iz","year":"2019"},{"key":"2022033118510842800_bib8","doi-asserted-by":"publisher","first-page":"2212","DOI":"10.18653\/v1\/D15-1263","article-title":"Better document-level sentiment analysis from RST discourse parsing","volume-title":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","author":"Bhatia","year":"2015"},{"key":"2022033118510842800_bib9","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1145\/279943.279962","article-title":"Combining labeled and unlabeled data with co-training","volume-title":"Proceedings of the 11th Annual Conference on Computational Learning Theory (COLT)","author":"Blum","year":"1998"},{"key":"2022033118510842800_bib10","unstructured":"Lynn\n              Carlson\n             and DanielMarcu. 2001. Discourse tagging reference manual. Technical Report ISI-TR-545. University California Information Sciences Institute."},{"key":"2022033118510842800_bib11","doi-asserted-by":"publisher","DOI":"10.3115\/1118078.1118083","article-title":"Building a discourse-tagged corpus in the framework of Rhetorical Structure Theory","volume-title":"Proceedings of the 2nd SIGdial Workshop on Discourse and Dialogue","author":"Carlson","year":"2001"},{"key":"2022033118510842800_bib12","doi-asserted-by":"publisher","first-page":"740","DOI":"10.3115\/v1\/D14-1082","article-title":"A fast and accurate dependency parser using neural networks","volume-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Chen","year":"2014"},{"key":"2022033118510842800_bib13","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)","author":"Devlin","year":"2019"},{"key":"2022033118510842800_bib14","article-title":"Deep biaffine attention for neural dependency parsing","volume-title":"Proceedings of the 5th International Conference on Learning Representations (ICLR)","author":"Dozat","year":"2017"},{"key":"2022033118510842800_bib15","doi-asserted-by":"publisher","first-page":"1998","DOI":"10.18653\/v1\/P16-1188","article-title":"Learning-based single-document summarization with compression and anaphoricity constraints","volume-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL2016)","author":"Durrett","year":"2016"},{"key":"2022033118510842800_bib16","first-page":"511","article-title":"A linear-time bottom-up discourse parser with constraints and post-editing","volume-title":"Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Feng","year":"2014"},{"key":"2022033118510842800_bib17","first-page":"584","article-title":"Leveraging discourse information effectively for authorship attribution","volume-title":"Proceedings of the The 8th International Joint Conference on Natural Language Processing (IJCNLP)","author":"Ferracane","year":"2017"},{"key":"2022033118510842800_bib18","doi-asserted-by":"crossref","first-page":"160","DOI":"10.18653\/v1\/2020.codi-1.17","article-title":"Coreference for discourse parsing: A neural approach","volume-title":"Proceedings of the First Workshop on Computational Approaches to Discourse","author":"Guz","year":"2020"},{"key":"2022033118510842800_bib19","first-page":"399","article-title":"A semi-supervised approach to improve classification of infrequent discourse relations using feature vector extension","volume-title":"Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Hernault","year":"2010"},{"issue":"3","key":"2022033118510842800_bib20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.5087\/dad.2010.003","article-title":"HILDA: A discourse parser using support vector machine classification","volume":"1","author":"Hernault","year":"2010","journal-title":"Dialogue & Discourse"},{"key":"2022033118510842800_bib21","first-page":"1515","article-title":"Single-document summarization as a tree knapsack problem","volume-title":"Proceedings of the 2013 Conference of Empirical Methods in Natural Language Processing (EMNLP)","author":"Hirao","year":"2013"},{"key":"2022033118510842800_bib22","first-page":"5010","article-title":"GSN: A graph-structured network for multi-party dialogues","volume-title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI)","author":"Wenpeng","year":"2019"},{"key":"2022033118510842800_bib23","doi-asserted-by":"publisher","first-page":"832","DOI":"10.3115\/1699571.1699621","article-title":"Self-training PCFG grammars with latent annotations across languages","volume-title":"Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Huang","year":"2009"},{"key":"2022033118510842800_bib24","doi-asserted-by":"publisher","first-page":"2306","DOI":"10.18653\/v1\/D19-1235","article-title":"Predicting discourse structure using distant supervision from sentiment","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint conference on Natural Language Processing (EMNLP-IJCNLP)","author":"Huber","year":"2019"},{"key":"2022033118510842800_bib25","doi-asserted-by":"publisher","DOI":"10.1101\/2020.06.10.144196","article-title":"Evaluating the efficacy of RT-qPCR SARS-CoV-2 direct approaches in comparison to RNA extraction","author":"Israeli","year":"2020","journal-title":"BioRxiv preprint 2020.06.10.144196v1"},{"key":"2022033118510842800_bib26","doi-asserted-by":"publisher","first-page":"977","DOI":"10.3115\/v1\/P14-1092","article-title":"Discourse complements lexical semantics for non-factoid answer reranking","volume-title":"Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Jansen","year":"2014"},{"key":"2022033118510842800_bib27","first-page":"13","article-title":"Representation learning for text-level discourse parsing","volume-title":"Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Ji","year":"2014"},{"key":"2022033118510842800_bib28","first-page":"996","article-title":"Neural discourse structure for text categorization","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Ji","year":"2017"},{"key":"2022033118510842800_bib29","first-page":"2603","article-title":"Training data enrichment for infrequent discourse relations","volume-title":"Proceedings of the 26th International Conference on Computational Linguistics (COLING)","author":"Jiang","year":"2016"},{"key":"2022033118510842800_bib30","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1162\/tacl_a_00300","article-title":"SpanBERT: Improving pre-training by representing and predicting spans","volume":"8","author":"Joshi","year":"2019","journal-title":"Transactions of the Association for Computational Linguistics"},{"issue":"3","key":"2022033118510842800_bib31","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1162\/COLI_a_00226","article-title":"CODRA: A novel discriminative framework for rhetorical analysis","volume":"41","author":"Joty","year":"2015","journal-title":"Computational Linguistics"},{"key":"2022033118510842800_bib32","first-page":"486","article-title":"Combining intra- and multi-sentential rhetorical parsing for document-level discourse analysis","volume-title":"Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Joty","year":"2013"},{"key":"2022033118510842800_bib33","doi-asserted-by":"publisher","first-page":"5851","DOI":"10.18653\/v1\/P19-1586","article-title":"Low-resource deep entity resolution with transfer and active learning","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Kasai","year":"2019"},{"key":"2022033118510842800_bib34","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1162\/tacl_a_00101","article-title":"Simple and accurate dependency parsing using bidirectional LSTM feature representations","volume":"4","author":"Kiperwasser","year":"2016","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"2022033118510842800_bib35","doi-asserted-by":"publisher","first-page":"8099","DOI":"10.1609\/aaai.v34i05.6321","article-title":"Top-down RST parsing utilizing granularity levels in documents","volume-title":"Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI)","author":"Kobayashi","year":"2020"},{"key":"2022033118510842800_bib36","doi-asserted-by":"publisher","first-page":"1600","DOI":"10.18653\/v1\/2021.naacl-main.127","article-title":"Improving neural RST parsing model with silver agreement subtrees","volume-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)","author":"Kobayashi","year":"2021"},{"key":"2022033118510842800_bib37","doi-asserted-by":"publisher","first-page":"5797","DOI":"10.18653\/v1\/D19-1587","article-title":"Split of merge: Which is better for unsupervised RST parsing?","volume-title":"Proceedings of the 2019 Conference of Empirical Methods in Natural Language Processing (EMNLP),","author":"Kobayashi","year":"2019"},{"key":"2022033118510842800_bib38","doi-asserted-by":"publisher","first-page":"715","DOI":"10.18653\/v1\/2021.eacl-main.60","article-title":"Top-down discourse parsing via sequence labeling","volume-title":"Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL)","author":"Koto","year":"2021"},{"key":"2022033118510842800_bib39","first-page":"2642","article-title":"Molweni: A challenge multiparty dialogue-based machine reading comprehension dataset with discourse structure","volume-title":"Proceedings of the 28th International Conference on Computational Linguistics (COLING)","author":"Li","year":"2020"},{"key":"2022033118510842800_bib40","doi-asserted-by":"crossref","first-page":"2061","DOI":"10.3115\/v1\/D14-1220","article-title":"Recursive deep models for discourse parsing","volume-title":"Proceedings of the 2014 Conference of Empirical Methods in Natural Language Processing (EMNLP)","author":"Li","year":"2014"},{"key":"2022033118510842800_bib41","doi-asserted-by":"publisher","first-page":"362","DOI":"10.18653\/v1\/D16-1035","article-title":"Discourse parsing with attention-based hierarchical neural networks","volume-title":"Proceedings of the 2016 Conference of Empirical Methods in Natural Language Processing (EMNLP)","author":"Qi","year":"2016"},{"key":"2022033118510842800_bib42","first-page":"25","article-title":"Text-level discourse dependency parsing","volume-title":"Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Li","year":"2014"},{"key":"2022033118510842800_bib43","first-page":"344","article-title":"Active learning for dependency parsing with partial annotation","volume-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Li","year":"2016"},{"key":"2022033118510842800_bib44","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1162\/tacl_a_00005","article-title":"Learning structured text representations","volume":"6","author":"Liu","year":"2018","journal-title":"Transactions of the Assocication for Computational Linguistics"},{"key":"2022033118510842800_bib45","first-page":"147","article-title":"Discourse indicators for content selection in summarization","volume-title":"Proceedings of the SIGDIAL 2010 Conference","author":"Louis","year":"2010"},{"key":"2022033118510842800_bib46","doi-asserted-by":"crossref","first-page":"285","DOI":"10.18653\/v1\/W15-4640","article-title":"The ubuntu dialogue corpus: A large dataset for research in unstructured multi-turn dialogue systems","volume-title":"Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIDDIAL)","author":"Lowe","year":"2015"},{"issue":"3","key":"2022033118510842800_bib47","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1515\/text.1.1988.8.3.243","article-title":"Rhetorical Structure Theory: Towards a functional theory of text organization","volume":"8","author":"Mann","year":"1988","journal-title":"Text-Interdisciplinary Journal for the Study of Discourse"},{"key":"2022033118510842800_bib48","first-page":"365","article-title":"A decision-based approach to rhetorical parsing","volume-title":"Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Marcu","year":"1999"},{"key":"2022033118510842800_bib49","first-page":"152","article-title":"Effective self-training for parsing","volume-title":"Proceedings of the 2006 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)","author":"McClosky","year":"2006"},{"key":"2022033118510842800_bib50","doi-asserted-by":"publisher","first-page":"523","DOI":"10.3115\/1220575.1220641","article-title":"Non-projective dependency parsing using spanning tree algorithms","volume-title":"Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (EMNLP-HLT)","author":"McDonald","year":"2005"},{"issue":"2","key":"2022033118510842800_bib51","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1162\/coli_a_00314","article-title":"A dependency perspective on RST discourse parsing and evaluation","volume":"44","author":"Morey","year":"2018","journal-title":"Computational Linguistics"},{"key":"2022033118510842800_bib52","first-page":"1883","article-title":"Constrained decoding for text-level discourse parsing","volume-title":"Proceedings of the 24th International Conference on Computational Linguistics (COLING)","author":"Muller","year":"2012"},{"key":"2022033118510842800_bib53","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1162\/tacl_a_00312","article-title":"Unsupervised discourse constituency parsing using Viterbi EM","volume":"8","author":"Nishida","year":"2020","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"2022033118510842800_bib54","doi-asserted-by":"publisher","first-page":"50","DOI":"10.3115\/1613148.1613156","article-title":"Incrementality in deterministic dependency parsing","volume-title":"Proceedings of the ACL Workshop Incremental Parsing: Bringing Engineering and Cognition Together","author":"Nivre","year":"2004"},{"key":"2022033118510842800_bib55","doi-asserted-by":"publisher","first-page":"99","DOI":"10.18653\/v1\/N16-1013","article-title":"Integer linear programming for discourse parsing","volume-title":"Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)","author":"Perret","year":"2016"},{"key":"2022033118510842800_bib56","article-title":"The Penn Discourse TreeBank 2.0","volume-title":"Proceedings of the Sixth International Conference on Language Resources and Evaluation","author":"Prasad","year":"2008"},{"key":"2022033118510842800_bib57","doi-asserted-by":"publisher","first-page":"1171","DOI":"10.18653\/v1\/E17-1110","article-title":"Distant supervision for relation extraction beyond the sentence boundary","volume-title":"Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL)","author":"Quirk","year":"2017"},{"key":"2022033118510842800_bib58","first-page":"3574","article-title":"Data programming: Creating large training sets, quickly","volume-title":"Proceedings of the 30th International Conference on Neural Information Processing Systems (NIPS)","author":"Ratner","year":"2016"},{"key":"2022033118510842800_bib59","first-page":"616","article-title":"Self-training for enhancement and domain adaptationa of statistical parsers train on small datasets","volume-title":"Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Reichart","year":"2007"},{"key":"2022033118510842800_bib60","doi-asserted-by":"publisher","first-page":"1044","DOI":"10.18653\/v1\/P18-1096","article-title":"Strong baselines for neural semi-supervised learning under domain shift","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Ruder","year":"2018"},{"key":"2022033118510842800_bib61","doi-asserted-by":"publisher","first-page":"81","DOI":"10.3115\/1697236.1697253","article-title":"Analysis of discourse structure with syntactic dependencies and data-driven shift-reduce parsing","volume-title":"Proceedings of the 11th International Workshop on Parsing Technology (IWPT)","author":"Sagae","year":"2009"},{"key":"2022033118510842800_bib62","first-page":"2988","article-title":"Asymmetric tri-training for unsupervised domain adaptation","volume-title":"Proceedings of The 34th International Conference on Machine Learning (ICML)","author":"Saito","year":"2017"},{"key":"2022033118510842800_bib63","unstructured":"Burr\n              Settles\n            \n          . 2009. Active learning literature survey. Computer Sciences Technical Report 1648. University of Wisconsin\u2013Madison."},{"key":"2022033118510842800_bib64","doi-asserted-by":"publisher","first-page":"7007","DOI":"10.1609\/aaai.v33i01.33017007","article-title":"A deep sequential model for discourse parsing on multi-party dialogues","volume-title":"Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence (AAAI)","author":"Shi","year":"2019"},{"key":"2022033118510842800_bib65","first-page":"1065","article-title":"Semi-supervised dependency parsing using generalized tri-training","volume-title":"Proceedings of the 23rd International Conference on Computational Linguistics (COLING)","author":"S\u00f8aard","year":"2010"},{"key":"2022033118510842800_bib66","doi-asserted-by":"publisher","first-page":"236","DOI":"10.3115\/1073445.1073476","article-title":"Example selection for bootstrapping statistical parsers","volume-title":"Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)","author":"Steedman","year":"2003"},{"key":"2022033118510842800_bib67","doi-asserted-by":"publisher","first-page":"331","DOI":"10.3115\/1067807.1067851","article-title":"Bootstrapping statistical parsers from small datasets","volume-title":"Proceedings of the 10th Conference of the European Chapter of the Association for Computational Linguistics (EACL)","author":"Steedman","year":"2003"},{"key":"2022033118510842800_bib68","first-page":"665","article-title":"Semi-supervised sequential labeling and segmentation using giga-word scale unlabeled data","volume-title":"Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Suzuki","year":"2008"},{"key":"2022033118510842800_bib69","doi-asserted-by":"publisher","first-page":"735","DOI":"10.1145\/1277741.1277883","article-title":"Evaluating discourse-based answer extraction for why-question answering","volume-title":"Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","author":"Verberne","year":"2007"},{"key":"2022033118510842800_bib70","article-title":"CORD-19: The COVID-19 open research dataset","author":"Wang","year":"2020","journal-title":"arXiv preprint arXiv:2004.10706v4"},{"key":"2022033118510842800_bib71","doi-asserted-by":"publisher","first-page":"184","DOI":"10.18653\/v1\/P17-2029","article-title":"A two-stage parsing method for text-level discourse analysis","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Wang","year":"2017"},{"key":"2022033118510842800_bib72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1116","article-title":"Toward fast and accurate neural discourse segmentation","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"Wang","year":"2018"},{"key":"2022033118510842800_bib73","doi-asserted-by":"publisher","first-page":"323","DOI":"10.3115\/v1\/P15-1032","article-title":"Structured training for neural network transition-based parsing","volume-title":"Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (ACL-IJCNLP)","author":"Weiss","year":"2015"},{"key":"2022033118510842800_bib74","first-page":"5021","article-title":"Discourse-aware neural extractive text summarization","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Jiacheng","year":"2020"},{"key":"2022033118510842800_bib75","doi-asserted-by":"publisher","first-page":"444","DOI":"10.18653\/v1\/P18-2071","article-title":"SciDTB: Discourse dependency treebank for scientific abstracts","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"An","year":"2018"},{"key":"2022033118510842800_bib76","doi-asserted-by":"publisher","first-page":"189","DOI":"10.3115\/981658.981684","article-title":"Unsupervised word sense disambiguation rivaling supervised methods","volume-title":"Proceedings of the 33rd Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Yarowsky","year":"1995"},{"key":"2022033118510842800_bib77","doi-asserted-by":"publisher","first-page":"1834","DOI":"10.3115\/v1\/D14-1196","article-title":"Dependency-based discourse parser for single-document summarization","volume-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing","author":"Yoshida","year":"2014"},{"key":"2022033118510842800_bib78","doi-asserted-by":"publisher","first-page":"5782","DOI":"10.18653\/v1\/2021.acl-long.449","article-title":"Adapting unsupervised syntactic parsing methodology for discourse dependency parsing","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"Zhang","year":"2021"},{"key":"2022033118510842800_bib79","doi-asserted-by":"publisher","first-page":"6386","DOI":"10.18653\/v1\/2020.acl-main.569","article-title":"A top-down neural architecture towards text-level parsing of discourse rhetorical structure","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Zhang","year":"2020"},{"key":"2022033118510842800_bib80","doi-asserted-by":"crossref","DOI":"10.1109\/ICTAI.2004.48","article-title":"Democratic co-learning","volume-title":"Proceedings of the 16th IEEE International Conference on Tools with Artificial Intelligence (ICTAI)","author":"Zhou","year":"2004"},{"issue":"11","key":"2022033118510842800_bib81","doi-asserted-by":"publisher","first-page":"1529","DOI":"10.1109\/TKDE.2005.186","article-title":"Tri-training: Exploiting unlabeled data using three classifiers","volume":"17","author":"Zhou","year":"2005","journal-title":"IEEE Transactions on Knowledge and Data Engineering,"}],"container-title":["Transactions of the Association for Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00451\/1987031\/tacl_a_00451.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00451\/1987031\/tacl_a_00451.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,31]],"date-time":"2022-03-31T23:52:46Z","timestamp":1648770766000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/doi\/10.1162\/tacl_a_00451\/109472\/Out-of-Domain-Discourse-Dependency-Parsing-via"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":81,"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00451","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022]]},"published":{"date-parts":[[2022]]}}}