{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T15:48:36Z","timestamp":1762876116147},"reference-count":33,"publisher":"MIT Press - Journals","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computational Linguistics"],"published-print":{"date-parts":[[2020,1]]},"abstract":"<jats:p> We present a framework for generating natural language description from structured data such as tables; the problem comes under the category of data-to-text natural language generation (NLG). Modern data-to-text NLG systems typically use end-to-end statistical and neural architectures that learn from a limited amount of task-specific labeled data, and therefore exhibit limited scalability, domain-adaptability, and interpretability. Unlike these systems, ours is a modular, pipeline-based approach, and does not require task-specific parallel data. Rather, it relies on monolingual corpora and basic off-the-shelf NLP tools. This makes our system more scalable and easily adaptable to newer domains. <\/jats:p><jats:p> Our system utilizes a three-staged pipeline that: (i) converts entries in the structured data to canonical form, (ii) generates simple sentences for each atomic entry in the canonicalized representation, and (iii) combines the sentences to produce a coherent, fluent, and adequate paragraph description through sentence compounding and co-reference replacement modules. Experiments on a benchmark mixed-domain data set curated for paragraph description from tables reveals the superiority of our system over existing data-to-text approaches. We also demonstrate the robustness of our system in accepting other popular data sets covering diverse data types such as knowledge graphs and key-value maps. <\/jats:p>","DOI":"10.1162\/coli_a_00363","type":"journal-article","created":{"date-parts":[[2019,10,8]],"date-time":"2019-10-08T14:59:06Z","timestamp":1570546746000},"page":"737-763","source":"Crossref","is-referenced-by-count":9,"title":["Scalable Micro-planned Generation of Discourse from Structured Data"],"prefix":"10.1162","volume":"45","author":[{"given":"Anirban","family":"Laha","sequence":"first","affiliation":[{"name":"Mila, Universit\u00e9 de Montr\u00e9al."}]},{"given":"Parag","family":"Jain","sequence":"additional","affiliation":[{"name":"School of Informatics, University of Edinburgh."}]},{"given":"Abhijit","family":"Mishra","sequence":"additional","affiliation":[{"name":"IBM Research."}]},{"given":"Karthik","family":"Sankaranarayanan","sequence":"additional","affiliation":[{"name":"IBM Research."}]}],"member":"281","reference":[{"key":"bib1","author":"Ahn Sungjin","year":"2016","journal-title":"CoRR"},{"key":"bib2","first-page":"2670","volume-title":"IJCAI","volume":"7","author":"Banko Michele","year":"2007"},{"key":"bib3","author":"Bao Junwei","year":"2018","journal-title":"arXiv preprint arXiv:1805.11234"},{"key":"bib4","doi-asserted-by":"publisher","DOI":"10.3115\/1220575.1220617"},{"key":"bib5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1016"},{"key":"bib6","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390173"},{"key":"bib7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-6626"},{"key":"bib8","first-page":"35","volume-title":"Proceedings of the 26th Australasian Computer Science Conference-Volume 16","author":"Dale Robert","year":"2003"},{"key":"bib9","author":"Fevry Thibault","year":"2018","journal-title":"arXiv preprint arXiv:1809.02669"},{"key":"bib10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1017"},{"key":"bib11","first-page":"187","volume-title":"Sixth Workshop on SMT","author":"Heafield Kenneth","year":"2011"},{"key":"bib12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2098"},{"key":"bib13","doi-asserted-by":"publisher","DOI":"10.1162\/0891201042544893"},{"key":"bib14","author":"Klein Guillaume","year":"2017","journal-title":"CoRR"},{"key":"bib15","first-page":"1503","volume-title":"EMNLP","author":"Konstas Ioannis","year":"2013"},{"key":"bib16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1128"},{"key":"bib17","doi-asserted-by":"publisher","DOI":"10.3115\/1687878.1687893"},{"key":"bib18","author":"Liu Tianyu","year":"2017","journal-title":"arXiv preprint arXiv:1711.09724"},{"key":"bib19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1086"},{"key":"bib20","doi-asserted-by":"publisher","DOI":"10.3115\/1690219.1690287"},{"key":"bib21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1064"},{"key":"bib22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1139"},{"key":"bib23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-5525"},{"key":"bib24","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1142"},{"key":"bib25","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"bib26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-1036"},{"key":"bib27","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2005.06.006"},{"key":"bib28","first-page":"523","volume-title":"EMNLP-CoNLL","author":"Schmitz Michael","year":"2012"},{"key":"bib29","unstructured":"Schuler, Karin Kipper. 2005. Verbnet: A Broad-coverage, Comprehensive Verb Lexicon. Ph.D. thesis, University of Pennsylvania."},{"key":"bib30","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242667"},{"key":"bib31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1074"},{"key":"bib32","volume-title":"International Conference on Learning Representations (ICLR)","author":"Vinyals Oriol","year":"2016"},{"key":"bib33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1239"}],"container-title":["Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/coli_a_00363","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T21:28:28Z","timestamp":1615584508000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/coli\/article\/45\/4\/737-763\/93360"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1]]},"references-count":33,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2020,1]]}},"alternative-id":["10.1162\/coli_a_00363"],"URL":"https:\/\/doi.org\/10.1162\/coli_a_00363","relation":{},"ISSN":["0891-2017","1530-9312"],"issn-type":[{"value":"0891-2017","type":"print"},{"value":"1530-9312","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,1]]}}}