{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T08:48:01Z","timestamp":1783500481057,"version":"3.55.0"},"reference-count":43,"publisher":"MIT Press - Journals","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> Neural text classification models typically treat output labels as categorical variables that lack description and semantics. This forces their parametrization to be dependent on the label set size, and, hence, they are unable to scale to large label sets and generalize to unseen ones. Existing joint input-label text models overcome these issues by exploiting label descriptions, but they are unable to capture complex label relationships, have rigid parametrization, and their gains on unseen labels happen often at the expense of weak performance on the labels seen during training. In this paper, we propose a new input-label model that generalizes over previous such models, addresses their limitations, and does not compromise performance on seen labels. The model consists of a joint nonlinear input-label embedding with controllable capacity and a joint-space-dependent classification unit that is trained with cross-entropy loss to optimize classification performance. We evaluate models on full-resource and low- or zero-resource text classification of multilingual news and biomedical text with a large label set. Our model outperforms monolingual and multilingual models that do not leverage label semantics and previous joint input-label space models in both scenarios. <\/jats:p>","DOI":"10.1162\/tacl_a_00259","type":"journal-article","created":{"date-parts":[[2019,4,18]],"date-time":"2019-04-18T14:32:46Z","timestamp":1555597966000},"page":"139-155","source":"Crossref","is-referenced-by-count":50,"title":["GILE: A Generalized Input-Label Embedding for Text Classification"],"prefix":"10.1162","volume":"7","author":[{"given":"Nikolaos","family":"Pappas","sequence":"first","affiliation":[{"name":"Idiap Research Institute, Martigny 1920, Switzerland."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"Henderson","sequence":"additional","affiliation":[{"name":"Idiap Research Institute, Martigny 1920, Switzerland."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"281","reference":[{"key":"bib1","author":"Ammar Waleed","year":"2016","journal-title":"CoRR"},{"key":"bib2","first-page":"1896","volume-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)","author":"Augenstein Isabelle","year":"2018"},{"key":"bib3","first-page":"983","volume-title":"Proceedings of The 33rd International Conference on Machine Learning","volume":"48","author":"Belanger David","year":"2016"},{"key":"bib4","first-page":"1765","volume-title":"Advances in Neural Information Processing Systems 28","author":"Chen Jianshu","year":"2015"},{"key":"bib5","first-page":"1724","volume-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing","author":"Cho Kyunghyun","year":"2014"},{"key":"bib6","first-page":"2493","volume":"12","author":"Collobert Ronan","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"bib7","volume-title":"International Conference on Learning Representations","author":"Dauphin Yann N.","year":"2014"},{"key":"bib8","doi-asserted-by":"crossref","first-page":"268","DOI":"10.18653\/v1\/D16-1026","volume-title":"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing","author":"Firat Orhan","year":"2016"},{"key":"bib9","first-page":"2121","volume-title":"Advances in Neural Information Processing Systems 26","author":"Frome Andrea","year":"2013"},{"issue":"1","key":"bib10","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1109\/MSP.2017.2763441","volume":"35","author":"Yanwei Fu","year":"2018","journal-title":"IEEE Signal Processing Magazine"},{"key":"bib11","first-page":"103","volume-title":"Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Johnson Rie","year":"2015"},{"key":"bib12","first-page":"1746","volume-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing","author":"Kim Yoon","year":"2014"},{"key":"bib13","first-page":"1459","volume-title":"Proceedings of COLING 2012","author":"Klementiev Alexandre","year":"2012"},{"key":"bib14","first-page":"334","volume-title":"Proceedings of The 33rd International Conference on Machine Learning","author":"Kumar Ankit","year":"2015"},{"key":"bib15","first-page":"2267","volume-title":"Proceedings of the 29th AAAI Conference on Artificial Intelligence","author":"Lai Siwei","year":"2015"},{"key":"bib16","first-page":"1188","volume-title":"Proceedings of The 31st International Conference on Machine Learning","author":"Le Quoc V.","year":"2014"},{"key":"bib17","volume-title":"Predicting Structured Data","author":"LeCun Yann","year":"2006"},{"key":"bib18","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00067"},{"key":"bib19","doi-asserted-by":"crossref","first-page":"899","DOI":"10.18653\/v1\/D15-1106","volume-title":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","author":"Lin Rui","year":"2015"},{"key":"bib20","doi-asserted-by":"crossref","first-page":"1412","DOI":"10.18653\/v1\/D15-1166","volume-title":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","author":"Luong Thang","year":"2015"},{"key":"bib21","doi-asserted-by":"crossref","first-page":"488","DOI":"10.1007\/978-3-642-33709-3_35","volume-title":"Computer Vision \u2013 ECCV 2012","author":"Mensink Thomas","year":"2012"},{"key":"bib22","first-page":"3111","volume-title":"Advances in Neural Information Processing Systems 26","author":"Mikolov Tomas","year":"2013"},{"key":"bib23","first-page":"246","volume-title":"Proceedings of the Tenth International Workshop on Artificial Intelligence and Statistics","author":"Morin Frederic","year":"2005"},{"key":"bib24","unstructured":"Khalil Mrini, Nikolaos Pappas, and Andrei Popescu-Belis. 2017. Cross-lingual transfer for news article labeling: Benchmarking statistical and neural models. In Idiap Research Report, Idiap-RR-26-2017."},{"key":"bib25","first-page":"1948","volume-title":"Proceedings of the 13th AAAI Conference on Artificial Intelligence","author":"Nam Jinseok","year":"2016"},{"key":"bib26","volume-title":"International Conference on Learning Representations","author":"Norouzi Mohammad","year":"2014"},{"key":"bib27","first-page":"115","volume-title":"Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics","author":"Bo Pang","year":"2005"},{"key":"bib28","doi-asserted-by":"crossref","first-page":"73","DOI":"10.18653\/v1\/W18-6308","volume-title":"Proceedings of the Third Conference on Machine Translation: Research Papers","author":"Pappas Nikolaos","year":"2018"},{"key":"bib29","first-page":"1015","volume-title":"Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"Pappas Nikolaos","year":"2017"},{"key":"bib30","doi-asserted-by":"crossref","first-page":"379","DOI":"10.18653\/v1\/D15-1044","volume-title":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","author":"Rush Alexander M.","year":"2015"},{"key":"bib31","doi-asserted-by":"crossref","first-page":"1715","DOI":"10.18653\/v1\/P16-1162","volume-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Sennrich Rico","year":"2016"},{"key":"bib32","first-page":"2911","volume-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing","author":"Shu Lei","year":"2017"},{"key":"bib33","first-page":"935","volume-title":"Proceedings of the 26th International Conference on Neural Information Processing Systems","author":"Socher Richard","year":"2013"},{"key":"bib34","first-page":"3266","volume-title":"Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 2","author":"Srikumar Vivek","year":"2014"},{"key":"bib35","doi-asserted-by":"crossref","first-page":"1422","DOI":"10.18653\/v1\/D15-1167","volume-title":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","author":"Tang Duyu","year":"2015"},{"key":"bib36","doi-asserted-by":"crossref","first-page":"2321","DOI":"10.18653\/v1\/P18-1216","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Wang Guoyin","year":"2018"},{"issue":"1","key":"bib37","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1007\/s10994-010-5198-3","volume":"81","author":"Weston Jason","year":"2010","journal-title":"Mach. Learn."},{"key":"bib38","first-page":"2764","volume-title":"Proceedings of the Twenty-Second International Joint Con ference on Artificial Intelligence (Volume 3)","author":"Weston Jason","year":"2011"},{"key":"bib39","first-page":"1480","volume-title":"Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Yang Zichao","year":"2016"},{"key":"bib40","doi-asserted-by":"crossref","first-page":"244","DOI":"10.18653\/v1\/D15-1027","volume-title":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","author":"Yazdani Majid","year":"2015"},{"key":"bib41","volume-title":"Proceedings of the 32nd AAAI Conference on Artificial Intelligence","author":"Yeh Chih-Kuan","year":"2018"},{"key":"bib42","first-page":"649","volume-title":"Advances in Neural Infor mation Processing Systems 28","author":"Zhang Xiang","year":"2015"},{"key":"bib43","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Zhang Yang","year":"2016"}],"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_00259","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T21:39:20Z","timestamp":1615585160000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/43491"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":43,"alternative-id":["10.1162\/tacl_a_00259"],"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00259","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,11]]}}}