{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T22:05:45Z","timestamp":1773093945291,"version":"3.50.1"},"reference-count":36,"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>The performance of text classification has improved tremendously using intelligently engineered neural-based models, especially those injecting categorical metadata as additional information, e.g., using user\/product information for sentiment classification. This information has been used to modify parts of the model (e.g., word embeddings, attention mechanisms) such that results can be customized according to the metadata. We observe that current representation methods for categorical metadata, which are devised for human consumption, are not as effective as claimed in popular classification methods, outperformed even by simple concatenation of categorical features in the final layer of the sentence encoder. We conjecture that categorical features are harder to represent for machine use, as available context only indirectly describes the category, and even such context is often scarce (for tail category). To this end, we propose using basis vectors to effectively incorporate categorical metadata on various parts of a neural-based model. This additionally decreases the number of parameters dramatically, especially when the number of categorical features is large. Extensive experiments on various data sets with different properties are performed and show that through our method, we can represent categorical metadata more effectively to customize parts of the model, including unexplored ones, and increase the performance of the model greatly.<\/jats:p>","DOI":"10.1162\/tacl_a_00263","type":"journal-article","created":{"date-parts":[[2019,4,29]],"date-time":"2019-04-29T18:09:19Z","timestamp":1556561359000},"page":"201-215","source":"Crossref","is-referenced-by-count":14,"title":["Categorical Metadata Representation for Customized Text Classification"],"prefix":"10.1162","volume":"7","author":[{"given":"Jihyeok","family":"Kim","sequence":"first","affiliation":[{"name":"Yonsei University."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Reinald Kim","family":"Amplayo","sequence":"additional","affiliation":[{"name":"University of Edinburgh."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyungjae","family":"Lee","sequence":"additional","affiliation":[{"name":"Yonsei University."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sua","family":"Sung","sequence":"additional","affiliation":[{"name":"Yonsei University."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minji","family":"Seo","sequence":"additional","affiliation":[{"name":"Yonsei University."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seung-won","family":"Hwang","sequence":"additional","affiliation":[{"name":"Yonsei University."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"281","reference":[{"key":"bib1","doi-asserted-by":"crossref","first-page":"2535","DOI":"10.18653\/v1\/P18-1236","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Amplayo Reinald Kim","year":"2018"},{"key":"bib2","first-page":"3955","volume-title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI 2018","author":"Amplayo Reinald Kim","year":"2018"},{"key":"bib3","volume-title":"Proceedings of the 3rd International Conference on Learning Representations","author":"Bahdanau Dzmitry","year":"2015"},{"key":"bib4","volume-title":"Proceedings of the Workshop on Adaptation and Personalization for Web 2.0, AP WEB 2.0@UMAP","author":"Baruzzo Andrea","year":"2009"},{"key":"bib5","doi-asserted-by":"crossref","first-page":"1650","DOI":"10.18653\/v1\/D16-1171","volume-title":"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing","author":"Chen Huimin","year":"2016"},{"issue":"11","key":"bib6","doi-asserted-by":"crossref","first-page":"2911","DOI":"10.1007\/s00500-016-2273-0","volume":"21","author":"Chou Po-Hao","year":"2017","journal-title":"Soft Computing"},{"key":"bib7","first-page":"521","volume-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing","author":"Dou Zi-Yi","year":"2017"},{"key":"bib8","unstructured":"Alec Go, Richa Bhayani, and Lei Huang. 2009. Twitter sentiment classification using distant supervision. CS224N Project Report, Stanford, 1(12)."},{"key":"bib9","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"issue":"5","key":"bib10","doi-asserted-by":"crossref","first-page":"499","DOI":"10.1177\/0165551511417785","volume":"37","author":"Joorabchi Arash","year":"2011","journal-title":"Journal of Information Science"},{"key":"bib11","first-page":"1746","volume-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Kim Yoon","year":"2014"},{"key":"bib12","first-page":"208","volume-title":"Proceedings of the 2nd International Conference on Ubiquitous Information Management and Communication, ICUIMC 2008","author":"Lam Xuan Nhat","year":"2008"},{"issue":"4","key":"bib13","doi-asserted-by":"crossref","first-page":"594","DOI":"10.1109\/TPAMI.2006.79","volume":"28","author":"Li Fei-Fei","year":"2006","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"bib14","volume-title":"COLING 2002: The 19th International Conference on Computational Linguistics","author":"Li Xin","year":"2002"},{"key":"bib15","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":"bib16","doi-asserted-by":"crossref","first-page":"140","DOI":"10.18653\/v1\/W18-6220","volume-title":"Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis","author":"Long Yunfei","year":"2018"},{"key":"bib17","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":"bib18","first-page":"634","volume-title":"Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"Ma Dehong","year":"2017"},{"key":"bib19","author":"Mikolov Tomas","year":"2013","journal-title":"CoRR"},{"key":"bib20","volume-title":"Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing (EMNLP 2002)","author":"Bo Pang","year":"2002"},{"issue":"3","key":"bib21","doi-asserted-by":"crossref","first-page":"643","DOI":"10.1177\/107769900207900307","volume":"79","author":"Papacharissi Zizi","year":"2002","journal-title":"Journalism & Mass Communication Quarterly"},{"key":"bib22","doi-asserted-by":"crossref","first-page":"1532","DOI":"10.3115\/v1\/D14-1162","volume-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Pennington Jeffrey","year":"2014"},{"key":"bib23","first-page":"2227","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":"Peters Matthew","year":"2018"},{"issue":"16","key":"bib24","volume-title":"Proceedings of the 4th International Conference on Learning Representations","author":"Ravi Sachin","year":"2016"},{"key":"bib25","first-page":"487","volume-title":"UAI \u201904, Proceedings of the 20th Conference in Uncertainty in Artificial Intelligence","author":"Rosen-Zvi Michal","year":"2004"},{"issue":"1","key":"bib26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/505282.505283","volume":"34","author":"Sebastiani Fabrizio","year":"2002","journal-title":"ACM Computing Surveys"},{"key":"bib27","first-page":"151","volume-title":"Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing","author":"Socher Richard","year":"2011"},{"key":"bib28","first-page":"59","volume":"5","author":"Sun Dong-ting","year":"2012","journal-title":"Computer and Modernization"},{"key":"bib29","first-page":"1014","volume-title":"Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"Tang Duyu","year":"2015"},{"issue":"2","key":"bib30","first-page":"13:1","volume":"10","author":"Wang Wei","year":"2019","journal-title":"ACM Transactions on Intelligent Systems and Technology"},{"key":"bib31","doi-asserted-by":"crossref","first-page":"496","DOI":"10.18653\/v1\/P18-2079","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","author":"Yang Pengcheng","year":"2018"},{"key":"bib32","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":"bib33","volume":"1212","author":"Zeiler Matthew D.","year":"2012","journal-title":"CoRR"},{"issue":"2","key":"bib34","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1109\/TASLP.2016.2632521","volume":"25","author":"Zhao Rui","year":"2017","journal-title":"IEEE\/ACM Transactions on Audio, Speech and Languange Processing"},{"key":"bib35","first-page":"3485","volume-title":"Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers","author":"Zhou Peng","year":"2016"},{"key":"bib36","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1145\/3155133.3155193","volume-title":"Proceedings of the Eighth International Symposium on Information and Communication Technology","author":"Zhu Pengcheng","year":"2017"}],"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_00263","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,17]],"date-time":"2022-09-17T03:05:01Z","timestamp":1663383901000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/43497"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":36,"alternative-id":["10.1162\/tacl_a_00263"],"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00263","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,11]]}}}