{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T05:36:16Z","timestamp":1775280976732,"version":"3.50.1"},"reference-count":9,"publisher":"MIT Press - Journals","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["TACL"],"published-print":{"date-parts":[[2018,12]]},"abstract":"<jats:p> In this paper, we focus on learning structure-aware document representations from data without recourse to a discourse parser or additional annotations. Drawing inspiration from recent efforts to empower neural networks with a structural bias (Cheng et al., 2016; Kim et al., 2017), we propose a model that can encode a document while automatically inducing rich structural dependencies. Specifically, we embed a differentiable non-projective parsing algorithm into a neural model and use attention mechanisms to incorporate the structural biases. Experimental evaluations across different tasks and datasets show that the proposed model achieves state-of-the-art results on document modeling tasks while inducing intermediate structures which are both interpretable and meaningful. <\/jats:p>","DOI":"10.1162\/tacl_a_00005","type":"journal-article","created":{"date-parts":[[2018,12,10]],"date-time":"2018-12-10T19:32:50Z","timestamp":1544470370000},"page":"63-75","source":"Crossref","is-referenced-by-count":57,"title":["Learning Structured Text Representations"],"prefix":"10.1162","volume":"6","author":[{"given":"Yang","family":"Liu","sequence":"first","affiliation":[{"name":"Institute for Language, Cognition and Computation, School of Informatics, University of Edinburgh, 10 Crichton Street, Edinburgh EH8 9AB,"}]},{"given":"Mirella","family":"Lapata","sequence":"additional","affiliation":[{"name":"Institute for Language, Cognition and Computation, School of Informatics, University of Edinburgh, 10 Crichton Street, Edinburgh EH8 9AB,"}]}],"member":"281","reference":[{"issue":"1","key":"p_2","doi-asserted-by":"crossref","first-page":"S132","DOI":"10.1121\/1.2017061","volume":"65","author":"Baker James K.","year":"1979","journal-title":"The Journal of the Acoustical Society of America"},{"key":"p_3","doi-asserted-by":"publisher","DOI":"10.1162\/coli.2008.34.1.1"},{"issue":"10","key":"p_12","first-page":"1396","volume":"14","author":"Chu Yoeng-Jin","year":"1965","journal-title":"Scientia Sinica"},{"key":"p_15","first-page":"2121","volume":"12","author":"Duchi John","year":"2011","journal-title":"Journal of Machine Learning Research"},{"issue":"4","key":"p_16","doi-asserted-by":"crossref","first-page":"233","DOI":"10.6028\/jres.071B.032","volume":"71","author":"Edmonds Jack","year":"1967","journal-title":"Journal of Research of the national Bureau of Standards B"},{"key":"p_21","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"p_28","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00115"},{"issue":"3","key":"p_30","first-page":"243","volume":"8","author":"Mann William C.","year":"1988","journal-title":"Text-Interdisciplinary Journal for the Study of Discourse"},{"issue":"2","key":"p_47","first-page":"21","volume":"47","author":"Verberne Suzan","year":"2007","journal-title":"Discours et Document: Traitements Automatics"}],"container-title":["Transactions of the Association for Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/tacl_a_00005","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T21:37:49Z","timestamp":1615585069000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/43421"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":9,"alternative-id":["10.1162\/tacl_a_00005"],"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00005","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12]]}}}