{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T10:15:40Z","timestamp":1781518540237,"version":"3.54.1"},"reference-count":63,"publisher":"MIT Press","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Transactions of the Association for Computational Linguistics"],"published-print":{"date-parts":[[2019,11]]},"abstract":"<jats:p>When searching for information, a human reader first glances over a document, spots relevant sections, and then focuses on a few sentences for resolving her intention. However, the high variance of document structure complicates the identification of the salient topic of a given section at a glance. To tackle this challenge, we present SECTOR, a model to support machine reading systems by segmenting documents into coherent sections and assigning topic labels to each section. Our deep neural network architecture learns a latent topic embedding over the course of a document. This can be leveraged to classify local topics from plain text and segment a document at topic shifts. In addition, we contribute WikiSection, a publicly available data set with 242k labeled sections in English and German from two distinct domains: diseases and cities. From our extensive evaluation of 20 architectures, we report a highest score of 71.6% F1 for the segmentation and classification of 30 topics from the English city domain, scored by our SECTOR long short-term memory model with Bloom filter embeddings and bidirectional segmentation. This is a significant improvement of 29.5 points F1 over state-of-the-art CNN classifiers with baseline segmentation.<\/jats:p>","DOI":"10.1162\/tacl_a_00261","type":"journal-article","created":{"date-parts":[[2019,4,18]],"date-time":"2019-04-18T14:32:46Z","timestamp":1555597966000},"page":"169-184","source":"Crossref","is-referenced-by-count":48,"title":["SECTOR: A Neural Model for Coherent Topic Segmentation and Classification"],"prefix":"10.1162","volume":"7","author":[{"given":"Sebastian","family":"Arnold","sequence":"first","affiliation":[{"name":"Beuth University of Applied Sciences Berlin, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rudolf","family":"Schneider","sequence":"additional","affiliation":[{"name":"Beuth University of Applied Sciences Berlin, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philippe","family":"Cudr\u00e9-Mauroux","sequence":"additional","affiliation":[{"name":"University of Fribourg, Fribourg, Switzerland."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felix A.","family":"Gers","sequence":"additional","affiliation":[{"name":"Beuth University of Applied Sciences Berlin, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"L\u00f6ser","sequence":"additional","affiliation":[{"name":"Beuth University of Applied Sciences Berlin, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"281","reference":[{"issue":"23","key":"bib1","doi-asserted-by":"crossref","first-page":"3174","DOI":"10.1093\/bioinformatics\/btp548","volume":"25","author":"Agarwal Shashank","year":"2009","journal-title":"Bioinformatics"},{"key":"bib2","doi-asserted-by":"crossref","first-page":"118","DOI":"10.18653\/v1\/W17-5115","volume-title":"Proceedings of the 4th Workshop on Argument Mining","author":"Ajjour Yamen","year":"2017"},{"key":"bib3","author":"Alemi Alexander A.","year":"2015","journal-title":"CoRR"},{"key":"bib4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/978-1-4615-0933-2","volume-title":"Topic Detection and Tracking","author":"Allan James","year":"2002"},{"key":"bib5","first-page":"3","volume-title":"Eighth IEEE International Conference on Data Mining","author":"AlSumait Loulwah","year":"2008"},{"key":"bib6","volume-title":"ICLR 2017: 5th International Conference on Learning Representations","author":"Arora Sanjeev","year":"2017"},{"key":"bib7","doi-asserted-by":"crossref","first-page":"1274","DOI":"10.1109\/ICDMW.2015.6","volume-title":"2015 International Conference on Data Mining Workshop","author":"Bayomi M.","year":"2015"},{"issue":"1","key":"bib8","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1023\/A:1007506220214","volume":"34","author":"Beeferman Doug","year":"1999","journal-title":"Machine Learning"},{"key":"bib9","first-page":"953","volume-title":"Proceedings of the 26th International Conference on Computational Linguistics","author":"Bhatia Shraey","year":"2016"},{"key":"bib10","first-page":"993","volume":"3","author":"Blei David M.","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"bib11","first-page":"371","volume-title":"Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics","author":"Chen Harr","year":"2009"},{"key":"bib12","first-page":"26","volume-title":"Proceedings of the 1st North American Chapter of the Association for Computational Linguistics Conference","author":"Choi Freddy Y. Y.","year":"2000"},{"key":"bib13","first-page":"1513","volume-title":"Proceedings of the 21st International Joint Conference on Artifical Intelligence","author":"Cimiano Philipp","year":"2009"},{"key":"bib14","first-page":"1165","volume-title":"The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval","author":"Cohen Daniel","year":"2018"},{"key":"bib15","first-page":"1107","volume-title":"Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics","author":"Conneau Alexis","year":"2017"},{"key":"bib16","first-page":"1334","volume-title":"Proceedings of the Twenty-Second AAAI Conference on Artificial Intelligence","volume":"7","author":"Dias Ga\u00ebl","year":"2007"},{"key":"bib17","volume-title":"ICLR 2017: 5th International Conference on Learning Representations","author":"Dieng Adji B.","year":"2017"},{"key":"bib18","first-page":"190","volume-title":"Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Lan Du","year":"2013"},{"key":"bib19","first-page":"334","volume-title":"Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing","author":"Eisenstein Jacob","year":"2008"},{"issue":"11","key":"bib20","doi-asserted-by":"crossref","first-page":"964","DOI":"10.1145\/32206.32212","volume":"30","author":"Furnas George W.","year":"1987","journal-title":"Communications of the ACM"},{"key":"bib21","first-page":"1606","volume-title":"Proceedings of the Twentieth International Joint Conference on Artificial Intelligence","author":"Gabrilovich Evgeniy","year":"2007"},{"key":"bib22","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015015"},{"key":"bib23","doi-asserted-by":"crossref","first-page":"125","DOI":"10.18653\/v1\/S16-2016","volume-title":"Proceedings of the Fifth Joint Conference on Lexical and Computational Semantics","author":"Glava\u0161 Goran","year":"2016"},{"key":"bib24","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-24797-2","volume-title":"Supervised Sequence Labelling with Recurrent Neural Networks","volume":"385","author":"Graves Alex","year":"2012"},{"issue":"1","key":"bib25","first-page":"33","volume":"23","author":"Hearst Marti A.","year":"1997","journal-title":"Computational Linguistics"},{"key":"bib26","first-page":"1535","volume-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics","volume":"1","author":"Hewlett Daniel","year":"2016"},{"key":"bib27","first-page":"1367","volume-title":"Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Hill Felix","year":"2016"},{"issue":"6245","key":"bib28","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1126\/science.aaa8685","volume":"349","author":"Hirschberg Julia","year":"2015","journal-title":"Science"},{"key":"bib29","first-page":"29","volume-title":"Association for the Advancement of Artificial Intelligence 2018 Workshop on Affective Content Analysis","author":"Le Hoa T.","year":"2018"},{"key":"bib30","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"issue":"3","key":"bib31","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1023\/A:1026028229881","volume":"6","author":"Huang Xiangji","year":"2003","journal-title":"Information Retrieval"},{"key":"bib32","doi-asserted-by":"crossref","first-page":"1119","DOI":"10.1145\/1871437.1871579","volume-title":"Proceedings of the 19th ACM International Conference on Information and Knowledge Management","author":"Jeong Minwoo","year":"2010"},{"issue":"3","key":"bib33","doi-asserted-by":"crossref","first-page":"482","DOI":"10.1080\/00330124.2012.700499","volume":"65","author":"Jiang Bin","year":"2012","journal-title":"The Professional Geographer"},{"key":"bib34","first-page":"199","volume-title":"Proceedings of the DARPA Broadcast News Workshop","author":"Jin Hubert","year":"1999"},{"key":"bib35","first-page":"137","volume-title":"European Conference on Machine Learning","author":"Joachims Thorsten","year":"1998"},{"key":"bib36","first-page":"1746","volume-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing","author":"Kim Yoon","year":"2014"},{"key":"bib37","first-page":"469","volume-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)","volume":"2","author":"Koshorek Omri","year":"2018"},{"key":"bib38","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1145\/1008992.1009044","volume-title":"Proceedings of the 27th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Kumaran Giridhar","year":"2004"},{"key":"bib39","first-page":"1188","volume-title":"Proceedings of the 31st International Conference on Machine Learning","volume":"32","author":"Le Quoc V.","year":"2014"},{"key":"bib40","volume-title":"Predicting Structured Data","volume":"1","author":"LeCun Yann","year":"2006"},{"key":"bib41","first-page":"1","volume-title":"ISA Annual Convention","volume":"2","author":"Leetaru Kalev","year":"2013"},{"key":"bib42","first-page":"1057","volume-title":"Proceedings of the 25th International Conference on World Wide Web","author":"Liu Jialu","year":"2016"},{"key":"bib43","first-page":"375","volume-title":"Proceedings of the Eleventh International Conference on Information and Knowledge Management","author":"Liu Xiaoyong","year":"2002"},{"key":"bib44","first-page":"1205","volume-title":"The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval","author":"MacAvaney Sean","year":"2018"},{"key":"bib45","author":"Mikolov Tomas","year":"2013","journal-title":"CoRR"},{"key":"bib46","first-page":"340","volume-title":"Proceedings of the 21st International Conference Knowledge-Based and Intelligent Information & Engineering Systems","volume":"112","author":"Naili Marwa","year":"2017"},{"key":"bib47","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1145\/3121050.3121099","volume-title":"Proceedings of the ACM SIGIR International Conference on Theory of Information Retrieval","author":"Nanni Federico","year":"2017"},{"key":"bib48","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1016\/j.artint.2012.07.001","volume":"193","author":"Navigli Roberto","year":"2012","journal-title":"Artificial Intelligence"},{"issue":"3","key":"bib49","doi-asserted-by":"crossref","first-page":"036104","DOI":"10.1103\/PhysRevE.74.036104","volume":"74","author":"Newman Mark E. J.","year":"2006","journal-title":"Physical Review E"},{"key":"bib50","first-page":"665","volume-title":"Proceedings of the 41th International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Piccardi Tiziano","year":"2018"},{"key":"bib51","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1145\/2623330.2623651","volume-title":"Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Prabhu Yashoteja","year":"2014"},{"key":"bib52","first-page":"37","volume-title":"Proceedings of ACL 2012 Student Research Workshop","author":"Riedl Martin","year":"2012"},{"key":"bib53","first-page":"626","volume-title":"Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing","author":"Santos Cicero Nogueira dos","year":"2015"},{"key":"bib54","first-page":"512","volume-title":"Automatic Speech Recognition and Understanding Workshop","author":"Sehikh Imran","year":"2017"},{"key":"bib55","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1145\/3109859.3109876","volume-title":"Proceedings of the Eleventh ACM Conference on Recommender Systems","author":"Serr\u00e0 Joan","year":"2017"},{"key":"bib56","doi-asserted-by":"crossref","first-page":"1419","DOI":"10.1145\/2872427.2874809","volume-title":"Proceedings of the 25th International Conference on World Wide Web","author":"Tanon Thomas Pellissier","year":"2016"},{"key":"bib57","first-page":"2001","volume-title":"Proceedings of the Eighth International Conference on Language Resources and Evaluation","author":"Tepper Michael","year":"2012"},{"key":"bib58","first-page":"92","volume-title":"AAAI Technical Report FS-12-05 Information Retrieval and Knowledge Discovery in Biomedical Text","author":"Tsatsaronis George","year":"2012"},{"key":"bib59","doi-asserted-by":"crossref","first-page":"667","DOI":"10.1007\/978-0-387-09823-4_34","volume-title":"Data Mining and Knowledge Discovery Handbook","author":"Tsoumakas Grigorios","year":"2009"},{"key":"bib60","first-page":"499","volume-title":"Proceedings of the 39th Annual Meeting on Association for Computational Linguistics","author":"Utiyama Masao","year":"2001"},{"key":"bib61","first-page":"1340","volume-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing","author":"Wang Liang","year":"2017"},{"key":"bib62","doi-asserted-by":"crossref","first-page":"310","DOI":"10.1016\/j.neucom.2016.08.017","volume":"216","author":"Yeh Jui-Feng","year":"2016","journal-title":"Neurocomputing"},{"key":"bib63","first-page":"537","volume":"8","author":"Ziou Djemel","year":"1998","journal-title":"Pattern Recognition and Image Analysis"}],"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_00261","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,16]],"date-time":"2022-09-16T08:13:14Z","timestamp":1663315994000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/43514"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":63,"alternative-id":["10.1162\/tacl_a_00261"],"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00261","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,11]]}}}