{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T11:16:53Z","timestamp":1778757413902,"version":"3.51.4"},"reference-count":45,"publisher":"MIT Press - Journals","license":[{"start":{"date-parts":[[2021,4,6]],"date-time":"2021-04-06T00:00:00Z","timestamp":1617667200000},"content-version":"vor","delay-in-days":95,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,3,31]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>We present the Quantized Transformer (QT), an unsupervised system for extractive opinion summarization. QT is inspired by Vector- Quantized Variational Autoencoders, which we repurpose for popularity-driven summarization. It uses a clustering interpretation of the quantized space and a novel extraction algorithm to discover popular opinions among hundreds of reviews, a significant step towards opinion summarization of practical scope. In addition, QT enables controllable summarization without further training, by utilizing properties of the quantized space to extract aspect-specific summaries. We also make publicly available Space, a large-scale evaluation benchmark for opinion summarizers, comprising general and aspect-specific summaries for 50 hotels. Experiments demonstrate the promise of our approach, which is validated by human studies where judges showed clear preference for our method over competitive baselines.<\/jats:p>","DOI":"10.1162\/tacl_a_00366","type":"journal-article","created":{"date-parts":[[2021,4,15]],"date-time":"2021-04-15T00:41:24Z","timestamp":1618447284000},"page":"277-293","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":42,"title":["Extractive Opinion Summarization in Quantized Transformer Spaces"],"prefix":"10.1162","volume":"9","author":[{"given":"Stefanos","family":"Angelidis","sequence":"first","affiliation":[{"name":"University of Edinburgh, United Kingdom. s.angelidis@ed.ac.uk"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Reinald Kim","family":"Amplayo","sequence":"additional","affiliation":[{"name":"University of Edinburgh, United Kingdom. reinald.kim@ed.ac.uk"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshihiko","family":"Suhara","sequence":"additional","affiliation":[{"name":"Megagon Labs, United States. yoshi@megagon.ai"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolan","family":"Wang","sequence":"additional","affiliation":[{"name":"Megagon Labs, United States. xiaolan@megagon.ai"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mirella","family":"Lapata","sequence":"additional","affiliation":[{"name":"University of Edinburgh, United Kingdom. mlap@inf.ed.ac.uk"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"281","published-online":{"date-parts":[[2021,3,31]]},"reference":[{"key":"2021060823403785700_bib1","article-title":"Informative and controllable opinion summarization","author":"Amplayo","year":"2019","journal-title":"arXiv preprint arXiv:1909.02322v1"},{"key":"2021060823403785700_bib2","doi-asserted-by":"crossref","first-page":"1934","DOI":"10.18653\/v1\/2020.acl-main.175","article-title":"Unsupervised opinion summarization with noising and denoising","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Amplayo","year":"2020"},{"key":"2021060823403785700_bib3","doi-asserted-by":"crossref","first-page":"3675","DOI":"10.18653\/v1\/D18-1403","article-title":"Summarizing opinions: Aspect extraction meets sentiment prediction and they are both weakly supervised","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"Angelidis","year":"2018"},{"key":"2021060823403785700_bib4","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio","year":"2013","journal-title":"arXiv preprint arXiv: 1308.3432v1"},{"key":"2021060823403785700_bib5","doi-asserted-by":"crossref","first-page":"5151","DOI":"10.18653\/v1\/2020.acl-main.461","article-title":"Unsupervised opinion summarization as copycat-review generation","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Bra\u017einskas","year":"2020"},{"key":"2021060823403785700_bib6","first-page":"2153","article-title":"Ranking with recursive neural networks and its application to multi-document summarization","volume-title":"Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence","author":"Cao","year":"2015"},{"key":"2021060823403785700_bib7","article-title":"Multi-document summarization of evaluative text","volume-title":"11th Conference of the European Chapter of the Association for Computational Linguistics","author":"Carenini","year":"2006"},{"key":"2021060823403785700_bib8","doi-asserted-by":"crossref","first-page":"484","DOI":"10.18653\/v1\/P16-1046","article-title":"Neural summarization by extracting sentences and words","volume-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Cheng","year":"2016"},{"key":"2021060823403785700_bib9","first-page":"1223","article-title":"MeanSum: A neural model for unsupervised multi-document abstractive summarization","volume-title":"Proceedings of the 36th International Conference on Machine Learning, volume 97 of Proceedings of Machine Learning Research","author":"Chu","year":"2019"},{"key":"2021060823403785700_bib10","doi-asserted-by":"crossref","first-page":"42","DOI":"10.18653\/v1\/D19-5405","article-title":"Unsupervised aspect-based multi-document abstractive summarization","volume-title":"Proceedings of the 2nd Workshop on New Frontiers in Summarization","author":"Coavoux","year":"2019"},{"key":"2021060823403785700_bib11","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, Volume 1 (Long and Short Papers)","author":"Devlin","year":"2019"},{"key":"2021060823403785700_bib12","doi-asserted-by":"crossref","first-page":"54","DOI":"10.3115\/v1\/W14-4408","article-title":"A hybrid approach to multi-document summarization of opinions in reviews","volume-title":"Proceedings of the 8th International Natural Language Generation Conference (INLG)","author":"Fabbrizio","year":"2014"},{"issue":"1","key":"2021060823403785700_bib13","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1613\/jair.1523","article-title":"Lexrank: Graph-based lexical centrality as salience in text summarization","volume":"22","author":"Erkan","year":"2004","journal-title":"Journal Of Artificial Intelligence Research"},{"key":"2021060823403785700_bib14","first-page":"340","article-title":"Opinosis: A graph based approach to abstractive summarization of highly redundant opinions","volume-title":"Proceedings of the 23rd International Conference on Computational Linguistics (COLING 2010)","author":"Ganesan","year":"2010"},{"key":"2021060823403785700_bib15","article-title":"The curious case of neural text degeneration","volume-title":"8th International Conference on Learning Representations, ICLR 2020, Virtual Conference, Apr 26th - May 1st","author":"Holtzman","year":"2020"},{"key":"2021060823403785700_bib16","first-page":"168","article-title":"Mining and summarizing customer reviews","volume-title":"Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Minqing","year":"2004"},{"key":"2021060823403785700_bib17","first-page":"487","article-title":"Opinions summarization: Aspect similarity recognition relaxes the constraint of predefined aspects","volume-title":"Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)","author":"Tien","year":"2019"},{"key":"2021060823403785700_bib18","doi-asserted-by":"crossref","first-page":"2142","DOI":"10.18653\/v1\/P19-1206","article-title":"Unsupervised neural single-document summarization of reviews via learning latent discourse structure and its ranking","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Isonuma","year":"2019"},{"key":"2021060823403785700_bib19","article-title":"Discrete autoencoders for sequence models","volume":"abs\/1801.09797v1","author":"Kaiser","year":"2018","journal-title":"ArXiv"},{"key":"2021060823403785700_bib20","article-title":"Auto-encoding variational Bayes","volume":"abs \/1312.6114v10","author":"Kingma","year":"2014","journal-title":"CoRR"},{"key":"2021060823403785700_bib21","first-page":"388","article-title":"Statistical significance tests for machine translation evaluation","volume-title":"Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing","author":"Koehn","year":"2004"},{"key":"2021060823403785700_bib22","article-title":"Generating Wikipedia by summarizing long sequences","volume-title":"6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 \u2013 May 3, 2018, Conference Track Proceedings","author":"Liu","year":"2018"},{"key":"2021060823403785700_bib23","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9781107337855","volume-title":"Best-worst Scaling: Theory, Methods and Applications","author":"Louviere","year":"2015"},{"key":"2021060823403785700_bib24","article-title":"The concrete distribution: A continuous relaxation of discrete random variables","volume-title":"International Conference on Learning Representations","author":"Maddison","year":"2017"},{"key":"2021060823403785700_bib25","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/978-3-319-06028-6_23","article-title":"Hierarchical multi-label conditional random fields for aspect-oriented opinion mining","volume-title":"Advances in Information Retrieval","author":"Marcheggiani","year":"2014"},{"key":"2021060823403785700_bib26","doi-asserted-by":"crossref","first-page":"617","DOI":"10.1145\/3366423.3380144","article-title":"Snippext: Semi-supervised opinion mining with augmented data","volume-title":"Proceedings of The Web Conference 2020","author":"Miao","year":"2020"},{"key":"2021060823403785700_bib27","first-page":"1747","article-title":"Ranking sentences for extractive summarization with reinforcement learning","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":"Narayan","year":"2018"},{"key":"2021060823403785700_bib28","first-page":"6306","article-title":"Neural discrete representation learning","volume-title":"Advances in Neural Information Processing Systems 30","author":"van den Oord","year":"2017"},{"key":"2021060823403785700_bib29","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1145\/3397271.3401439","article-title":"Large scale abstractive multi-review summarization (LSARS) via aspect alignment","volume-title":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Pan","year":"2020"},{"issue":"1\u20142","key":"2021060823403785700_bib30","first-page":"1","article-title":"Opinion mining and sentiment analysis","volume":"2","author":"Bo","year":"2008","journal-title":"Foundations and Trends in Information Retrieval"},{"key":"2021060823403785700_bib31","doi-asserted-by":"crossref","first-page":"5107","DOI":"10.18653\/v1\/P19-1504","article-title":"Generating summaries with topic templates and structured convolutional decoders","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Perez-Beltrachini","year":"2019"},{"key":"2021060823403785700_bib32","doi-asserted-by":"crossref","first-page":"1059","DOI":"10.18653\/v1\/P19-1101","article-title":"A simple theoretical model of importance for summarization","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Peyrard","year":"2019"},{"key":"2021060823403785700_bib33","first-page":"375","article-title":"Evaluation challenges in large-scale document summarization","volume-title":"Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics","author":"Radev","year":"2003"},{"key":"2021060823403785700_bib34","article-title":"Learning to generate reviews and discovering sentiment","author":"Radford","year":"2017","journal-title":"arXiv preprint arXiv:1704.01444v2"},{"key":"2021060823403785700_bib35","doi-asserted-by":"crossref","first-page":"4035","DOI":"10.18653\/v1\/D18-1437","article-title":"Object hallucination in image captioning","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"Rohrbach","year":"2018"},{"key":"2021060823403785700_bib36","doi-asserted-by":"crossref","first-page":"6033","DOI":"10.18653\/v1\/P19-1605","article-title":"Unsupervised paraphrasing without translation","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Roy","year":"2019"},{"key":"2021060823403785700_bib37","article-title":"Theory and experiments on vector quantized autoencoders","author":"Roy","year":"2018","journal-title":"arXiv preprint arXiv:1805.11063v2"},{"key":"2021060823403785700_bib38","doi-asserted-by":"crossref","first-page":"1073","DOI":"10.18653\/v1\/P17-1099","article-title":"Get to the point: Summarization with pointer-generator networks","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"See","year":"2017"},{"key":"2021060823403785700_bib39","doi-asserted-by":"crossref","first-page":"5789","DOI":"10.18653\/v1\/2020.acl-main.513","article-title":"OpinionDigest: A simple framework for opinion summarization","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Suhara","year":"2020"},{"key":"2021060823403785700_bib40","doi-asserted-by":"crossref","first-page":"2061","DOI":"10.1145\/3357384.3358142","article-title":"Aspect and opinion aware abstractive review summarization with reinforced hard typed decoder","volume-title":"Proceedings of the 28th ACM International Conference on Information and Knowledge Management","author":"Tian","year":"2019"},{"issue":"nov","key":"2021060823403785700_bib41","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"2021060823403785700_bib42","first-page":"5998","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems 30","author":"Vaswani","year":"2017"},{"key":"2021060823403785700_bib43","doi-asserted-by":"crossref","first-page":"783","DOI":"10.1145\/1835804.1835903","article-title":"Latent aspect rating analysis on review text data: A rating regression approach","volume-title":"Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Wang","year":"2010"},{"key":"2021060823403785700_bib44","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1145\/3366424.3383535","article-title":"ExtremeReader: An interactive explorer for customizable and explainable review summarization","volume-title":"Companion Proceedings of the Web Conference 2020","author":"Wang","year":"2020"},{"key":"2021060823403785700_bib45","doi-asserted-by":"crossref","first-page":"452","DOI":"10.18653\/v1\/K17-1045","article-title":"Graph-based neural multi-document summarization","volume-title":"Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)","author":"Yasunaga","year":"2017"}],"container-title":["Transactions of the Association for Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00366\/1924181\/tacl_a_00366.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00366\/1924181\/tacl_a_00366.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,9]],"date-time":"2021-06-09T09:47:34Z","timestamp":1623232054000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/doi\/10.1162\/tacl_a_00366\/98621\/Extractive-Opinion-Summarization-in-Quantized"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00366","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021]]},"published":{"date-parts":[[2021]]}}}