{"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":1775280976685,"version":"3.50.1"},"reference-count":52,"publisher":"MIT Press","license":[{"start":{"date-parts":[[2022,5,17]],"date-time":"2022-05-17T00:00:00Z","timestamp":1652745600000},"content-version":"vor","delay-in-days":136,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,5,4]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The availability of large-scale datasets has driven the development of neural models that create generic summaries for single or multiple documents. For query-focused summarization (QFS), labeled training data in the form of queries, documents, and summaries is not readily available. We provide a unified modeling framework for any kind of summarization, under the assumption that all summaries are a response to a query, which is observed in the case of QFS and latent in the case of generic summarization. We model queries as discrete latent variables over document tokens, and learn representations compatible with observed and unobserved query verbalizations. Our framework formulates summarization as a generative process, and jointly optimizes a latent query model and a conditional language model. Despite learning from generic summarization data only, our approach outperforms strong comparison systems across benchmarks, query types, document settings, and target domains.1<\/jats:p>","DOI":"10.1162\/tacl_a_00480","type":"journal-article","created":{"date-parts":[[2022,5,17]],"date-time":"2022-05-17T15:03:21Z","timestamp":1652799801000},"page":"623-638","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":8,"title":["Document Summarization with Latent Queries"],"prefix":"10.1162","volume":"10","author":[{"given":"Yumo","family":"Xu","sequence":"first","affiliation":[{"name":"Institute for Language, Cognition and Computation, School of Informatics, University of Edinburgh, 10 Crichton Street, Edinburgh EH8 9AB, United Kingdom. yumo.xu@ed.ac.uk"}]},{"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, United Kingdom. mlap@inf.ed.ac.uk"}]}],"member":"281","published-online":{"date-parts":[[2022,5,4]]},"reference":[{"key":"2022051714395828100_bib1","doi-asserted-by":"crossref","first-page":"80","DOI":"10.18653\/v1\/2020.inlg-1.11","article-title":"Towards generating query to perform query focused abstractive summarization using pre-trained model","volume-title":"Proceedings of the 13th International Conference on Natural Language Generation","author":"Abdullah","year":"2020"},{"key":"2022051714395828100_bib2","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1007\/978-3-642-20161-5_64","article-title":"Improving query focused summarization using look-ahead strategy","volume-title":"Proceedings of the 33rd European Conference on Advances in Information Retrieval","author":"Badrinath","year":"2011"},{"key":"2022051714395828100_bib3","article-title":"MS MARCO: A human generated machine reading comprehension dataset","author":"Bajaj","year":"2016","journal-title":"arXiv preprint arXiv:1611.09268"},{"key":"2022051714395828100_bib4","first-page":"2573","article-title":"Topic concentration in query focused summarization datasets","volume-title":"Proceedings of the 30th AAAI Conference on Artificial Intelligence","author":"Baumel","year":"2016"},{"key":"2022051714395828100_bib5","article-title":"Query focused abstractive summarization: Incorporating query relevance, multi-document coverage, and summary length constraints into seq2seq models","author":"Baumel","year":"2018","journal-title":"arXiv preprint arXiv:1801 .07704"},{"key":"2022051714395828100_bib6","doi-asserted-by":"crossref","first-page":"152","DOI":"10.18653\/v1\/P18-1015","article-title":"Retrieve, rerank and rewrite: Soft template based neural summarization","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Cao","year":"2018"},{"key":"2022051714395828100_bib7","doi-asserted-by":"publisher","first-page":"5935","DOI":"10.18653\/v1\/2021.naacl-main.475","article-title":"Improving faithfulness in abstractive summarization with contrast candidate generation and selection","volume-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Chen","year":"2021"},{"key":"2022051714395828100_bib8","first-page":"1","article-title":"Overview of duc 2005","volume-title":"Proceedings of the 2005 Document Understanding Conference","author":"Dang","year":"2005"},{"key":"2022051714395828100_bib9","doi-asserted-by":"publisher","first-page":"48","DOI":"10.3115\/1654679.1654689","article-title":"DUC 2005: Evaluation of question-focused summarization systems","volume-title":"Proceedings of the Workshop on Task-Focused Summarization and Question Answering","author":"Dang","year":"2006"},{"key":"2022051714395828100_bib10","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","author":"Devlin","year":"2019"},{"key":"2022051714395828100_bib11","doi-asserted-by":"publisher","first-page":"4830","DOI":"10.18653\/v1\/2021.naacl-main.384","article-title":"GSum: A general framework for guided neural abstractive summarization","volume-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Dou","year":"2021"},{"key":"2022051714395828100_bib12","doi-asserted-by":"publisher","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":"2022051714395828100_bib13","doi-asserted-by":"publisher","first-page":"4098","DOI":"10.18653\/v1\/D18-1443","article-title":"Bottom-up abstractive summarization","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"Gehrmann","year":"2018"},{"key":"2022051714395828100_bib14","first-page":"pages 1693\u2013pages 1701","article-title":"Teaching machines to read and comprehend","volume-title":"Proceedings of the 28th International Conference on Neural Information Processing Systems","author":"Hermann","year":"2015"},{"key":"2022051714395828100_bib15","article-title":"beta-vae: Learning basic visual concepts with a constrained variational framework","volume-title":"Proceedings of the 5th International Conference on Learning Representations","author":"Higgins","year":"2017"},{"key":"2022051714395828100_bib16","article-title":"Overview of DUC 2006","volume-title":"Proceedings of the 2006 Document Understanding Conference","author":"Hoa","year":"2006"},{"key":"2022051714395828100_bib17","article-title":"Categorical reparameterization with gumbel- softmax","author":"Jang","year":"2016","journal-title":"arXiv preprint arXiv:1611.01144"},{"key":"2022051714395828100_bib18","doi-asserted-by":"publisher","first-page":"8026","DOI":"10.1609\/aaai.v34i05.6312","article-title":"Semsum: Semantic dependency guided neural abstractive summarization","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Jin","year":"2020"},{"key":"2022051714395828100_bib19","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1525\/9780520411586-036","article-title":"Nonlinear programming","volume-title":"Proceedings of the Second Berkeley Symposium on Mathematical Statistics and Probability","author":"Kuhn","year":"1951"},{"key":"2022051714395828100_bib20","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1162\/tacl_a_00276","article-title":"Natural questions: a benchmark for question answering research","volume":"7","author":"Kwiatkowski","year":"2019","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"2022051714395828100_bib21","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1007\/978-3-030-47358-7_35","article-title":"Query focused abstractive summarization via incorporating query relevance and transfer learning with transformer models","volume-title":"Canadian Conference on Artificial Intelligence","author":"Laskar","year":"2020"},{"key":"2022051714395828100_bib22","doi-asserted-by":"crossref","first-page":"5647","DOI":"10.18653\/v1\/2020.coling-main.495","article-title":"WSL-DS: Weakly supervised learning with distant supervision for query focused multi-document abstractive summarization","volume-title":"Proceedings of the 28th International Conference on Computational Linguistics","author":"Laskar","year":"2020"},{"key":"2022051714395828100_bib23","doi-asserted-by":"publisher","first-page":"4131","DOI":"10.18653\/v1\/D18-1446","article-title":"Adapting the neural encoder-decoder framework from single to multi-document summarization","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"Lebanoff","year":"2018"},{"key":"2022051714395828100_bib24","doi-asserted-by":"publisher","first-page":"7871","DOI":"10.18653\/v1\/2020.acl-main.703","article-title":"BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Lewis","year":"2020"},{"key":"2022051714395828100_bib25","first-page":"2081","article-title":"Cascaded attention based unsupervised information distillation for compressive summarization","volume-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing","author":"Li","year":"2017"},{"key":"2022051714395828100_bib26","first-page":"3497","article-title":"Salience estimation via variational auto-encoders for multi-document summarization","volume-title":"Proceedings of the 31th AAAI Conference on Artificial Intelligence","author":"Li","year":"2017"},{"key":"2022051714395828100_bib27","first-page":"71","article-title":"Automatic evaluation of summaries using n-gram co-occurrence statistics","volume-title":"Proceedings of the 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics","author":"Lin","year":"2003"},{"key":"2022051714395828100_bib28","article-title":"Generating Wikipedia by summarizing long sequences","volume-title":"Proceedings of the 6th International Conference on Learning Representations","author":"Liu","year":"2018"},{"key":"2022051714395828100_bib29","doi-asserted-by":"publisher","first-page":"5070","DOI":"10.18653\/v1\/P19-1500","article-title":"Hierarchical transformers for multi-document summarization","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Liu","year":"2019"},{"key":"2022051714395828100_bib30","doi-asserted-by":"publisher","first-page":"3730","DOI":"10.18653\/v1\/D19-1387","article-title":"Text summarization with pretrained encoders","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing","author":"Liu","year":"2019"},{"key":"2022051714395828100_bib31","doi-asserted-by":"publisher","first-page":"280","DOI":"10.18653\/v1\/K16-1028","article-title":"Abstractive text summarization using sequence-to-sequence RNNs and beyond","volume-title":"Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning","author":"Nallapati","year":"2016"},{"key":"2022051714395828100_bib32","doi-asserted-by":"publisher","first-page":"1797","DOI":"10.18653\/v1\/D18-1206","article-title":"Don\u2019t give me the details, just the summary! Topic-aware convolutional neural networks for extreme summarization","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"Narayan","year":"2018"},{"key":"2022051714395828100_bib33","doi-asserted-by":"publisher","first-page":"1063","DOI":"10.18653\/v1\/P17-1098","article-title":"Diversity driven attention model for query-based abstractive summarization","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics","author":"Nema","year":"2017"},{"key":"2022051714395828100_bib34","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1613\/jair.1.12522","article-title":"Multi-document summarization with determinantal point process attention","volume":"71","author":"Perez-Beltrachini","year":"2021","journal-title":"Journal of Artificial Intelligence Research"},{"key":"2022051714395828100_bib35","doi-asserted-by":"publisher","first-page":"5107","DOI":"10.1613\/jair.1.12522","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":"2022051714395828100_bib36","doi-asserted-by":"publisher","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":"2022051714395828100_bib37","doi-asserted-by":"publisher","first-page":"2383","DOI":"10.18653\/v1\/D16-1264","article-title":"SQuAD: 100,000+ questions for machine comprehension of text","volume-title":"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing","author":"Rajpurkar","year":"2016"},{"key":"2022051714395828100_bib38","doi-asserted-by":"crossref","first-page":"379","DOI":"10.18653\/v1\/D15-1044","article-title":"A neural attention model for abstractive sentence summarization","volume-title":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","author":"Rush","year":"2015"},{"key":"2022051714395828100_bib39","first-page":"1073","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","author":"See","year":"2017"},{"key":"2022051714395828100_bib40","doi-asserted-by":"publisher","first-page":"1715","DOI":"10.18653\/v1\/P16-1162","article-title":"Neural machine translation of rare words with subword units","volume-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Sennrich","year":"2016"},{"key":"2022051714395828100_bib41","first-page":"2377","article-title":"Training very deep networks","volume-title":"Proceedings of the 28th International Conference on Neural Information Processing Systems-Volume 2","author":"Srivastava","year":"2015"},{"key":"2022051714395828100_bib42","doi-asserted-by":"publisher","first-page":"203","DOI":"10.18653\/v1\/D19-5827","article-title":"Generalizing question answering system with pre-trained language model fine-tuning","volume-title":"Proceedings of the 2nd Workshop on Machine Reading for Question Answering","author":"Su","year":"2019"},{"key":"2022051714395828100_bib43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.nlpcovid19-2.14","article-title":"CAiRE-COVID: A question answering and query-focused multi-document summarization system for COVID-19 scholarly information management","volume-title":"Proceedings of the 1st Workshop on NLP for COVID-19 at EMNLP 2020","author":"Su","year":"2020"},{"key":"2022051714395828100_bib44","article-title":"Sequence to sequence learning with neural networks","volume-title":"Advances in Neural Information Processing Systems","author":"Sutskever","year":"2014"},{"key":"2022051714395828100_bib45","first-page":"6000","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"2022051714395828100_bib46","first-page":"2903","article-title":"Manifold-ranking based topic-focused multi-document summarization","volume-title":"Proceedings of the 20th International Joint Conference on Artificial Intelligence","author":"Wan","year":"2007"},{"key":"2022051714395828100_bib47","first-page":"787","article-title":"CTSUM: Extracting more certain summaries for news articles","volume-title":"Proceedings of the 37th International ACM SIGIR Conference on Research & Development in Information Retrieval","author":"Wan","year":"2014"},{"key":"2022051714395828100_bib48","doi-asserted-by":"publisher","first-page":"485","DOI":"10.18653\/v1\/2020.emnlp-main.35","article-title":"Friendly topic assistant for transformer based abstractive summarization","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing","author":"Wang","year":"2020"},{"key":"2022051714395828100_bib49","first-page":"3632","article-title":"Coarse- to-fine query focused multi-document summarization","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing","author":"Yumo","year":"2020"},{"key":"2022051714395828100_bib50","first-page":"6096","article-title":"Generating query focused summaries from query-free resources","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"Yumo","year":"2021"},{"key":"2022051714395828100_bib51","doi-asserted-by":"publisher","first-page":"6197","DOI":"10.18653\/v1\/2020.acl-main.552","article-title":"Extractive summarization as text matching","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Zhong","year":"2020"},{"key":"2022051714395828100_bib52","article-title":"Transforming Wikipedia into augmented data for query-focused summarization","author":"Zhu","year":"2019","journal-title":"arXiv preprint arXiv:1911.03324"}],"container-title":["Transactions of the Association for Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00480\/2022951\/tacl_a_00480.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00480\/2022951\/tacl_a_00480.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,25]],"date-time":"2024-09-25T06:45:55Z","timestamp":1727246755000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/doi\/10.1162\/tacl_a_00480\/111219\/Document-Summarization-with-Latent-Queries"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00480","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022]]},"published":{"date-parts":[[2022]]}}}