{"type":"ScholarlyArticle","title":"Text Rewriting Improves Semantic Role Labeling (Extended Abstract)","authors":[{"name":"Kristian Woodsend","slug":"kristian-woodsend","given":"Kristian","family":"Woodsend","affiliation":"Institute for Language , Cognition and Computation School of Informatics , University of Edinburgh 10 Crichton Street , Edinburgh EH8 9AB"},{"name":"Mirella Lapata","slug":"mirella-lapata","given":"Mirella","family":"Lapata","affiliation":"Institute for Language , Cognition and Computation School of Informatics , University of Edinburgh 10 Crichton Street , Edinburgh EH8 9AB"}],"abstract":"Large-scale annotated corpora are a prerequisite to developing high-performance NLP systems. Such corpora are expensive to produce, limited in size, often demanding linguistic expertise. In this paper we use text rewriting as a means of increasing the amount of labeled data available for model training. Our method uses automatically extracted rewrite rules from comparable corpora and bitexts to generate multiple versions of sentences annotated with gold standard labels. We apply this idea to semantic role labeling and show that a model trained on rewritten data outperforms the state of the art on the CoNLL-2009 benchmark dataset.","doi":"10.24963/ijcai.2017/729","url":"https://ijcai.org/proceedings/2017/729","pdf":"https://ijcai.org/proceedings/2017/0729.pdf","markdown":"https://ijcai.org/proceedings/2017/729.md","bibtex":"https://ijcai.org/proceedings/2017/bibtex/729","volume":{"slug":"2017","title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2017","url":"https://ijcai.org/proceedings/2017/","year":2017,"location":"Melbourne, Australia","dates":"19-25 August 2017","editors":"Carles Sierra","isbn":"978-0-9992411-0-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2017"},"section":"Journal track","track":"Journal track","number":729,"pages":{"first":5095,"last":5099},"keywords":["Natural Language Processing: Natural Language Processing","Natural Language Processing: Tagging, chunking, syntax, and parsing","Natural Language Processing: Natural Language Semantics","Natural Language Processing: Natural Language Generation"],"videos":[],"references":[{"position":1,"raw":"[Aho and Ullman, 1969] Alfred V. Aho and Jeffrey D. Ull- man. Syntax directed translations and the pushdown assembler. Journal of Computer and System Sciences, 3(1):37-56, 1969.","title":"Syntax directed translations and the pushdown assembler","authors":"Alfred V Aho, Jeffrey D Ullman","year":"1969","venue":"Journal of Computer and System Sciences","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bannard and Callison-Burch, 2005] Colin Bannard and Chris Callison-Burch. Paraphrasing with Bilingual Parallel Corpora. In Proceedings of the 43rd ACL, pages 597-604, Ann Arbor, MI, 2005.","title":"Paraphrasing with Bilingual Parallel Corpora","authors":"Callison-Burch ; Bannard, Colin Bannard, Chris Callison-Burch","year":"2005","venue":"Proceedings of the 43rd ACL","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Barzilay and McKeown, 2001] Regina Barzilay and Kathy McKeown. Extracting Paraphrases from a Parallel Corpus. In Proceedings of the ACL/EACL, pages 50-57, Toulouse, France, 2001.","title":"Extracting Paraphrases from a Parallel Corpus","authors":"Mckeown Barzilay, Regina Barzilay, Kathy Mckeown","year":"2001","venue":"Proceedings of the ACL/EACL","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Björkelund et al., 2009] Anders Björkelund, Love Hafdell, and Pierre Nugues. Multilingual semantic role labeling. In Proceedings of the Thirteenth Conference on Computa- tional Natural Language Learning (CoNLL 2009): Shared Task, pages 43-48, Boulder, Colorado, June 2009. Soft- ware retrieved from https://code.google.com/ p/mate-tools/.","title":"Multilingual semantic role labeling","authors":"Björkelund","year":"2009","venue":"Proceedings of the Thirteenth Conference on Computational Natural Language Learning (CoNLL 2009): Shared Task","doi":null,"url":"https://code.google.com/p/mate-tools/","internal_url":null},{"position":5,"raw":"[Callison-Burch, 2007] Chris Callison-Burch. Paraphrasing and Translation. PhD thesis, University of Edinburgh, 2007.","title":"Paraphrasing and Translation","authors":"Chris Callison-Burch","year":"2007","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Cohn and Lapata, 2009] Trevor Cohn and Mirella Lapata. Sentence Compression as Tree Transduction. Journal of Artificial Intelligence Research, 34:637-674, 2009.","title":"Sentence Compression as Tree Transduction","authors":"Trevor Cohn, Mirella Lapata","year":"2009","venue":"Journal of Artificial Intelligence Research","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Coster and Kauchak, 2011] William Coster and David Kauchak. Simple English Wikipedia: A New Text Simplification Task. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 665-669, Portland, Oregon, USA, June 2011.","title":"Simple English Wikipedia: A New Text Simplification Task","authors":"Kauchak Coster, William Coster, David Kauchak","year":"2011","venue":"Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Ganitkevitch et al., 2013] Juri Ganitkevitch, Benjamin Van Durme, and Chris Callison-Burch. PPDB: The Paraphrase Database. In Proceedings of the 2013 Conference of the North American Chapter of the Association for Com- putational Linguistics: Human Language Technologies, pages 758-764, Atlanta, Georgia, June 2013. We used the prepackaged \"small\" constituent syntactic subset of PPDB, retrieved from http://paraphrase.org.","title":"PPDB: The Paraphrase Database","authors":"Juri Ganitkevitch, Benjamin Van Durme, Chris Callison-Burch","year":"2013","venue":"Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","doi":null,"url":"http://paraphrase.org","internal_url":null},{"position":9,"raw":"[Gildea and Jurafsky, 2002] Daniel Gildea and Daniel Juraf- sky. Automatic Labeling of Semantic Roles. Computa- tional Linguistics, 28(3):245-288, 2002.","title":"Automatic Labeling of Semantic Roles","authors":"Daniel Gildea, Daniel Jurafsky","year":"2002","venue":"Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Heilman and Smith, 2010] Michael Heilman and Noah Smith. Extracting Simplified Statements for Factual Ques- tion Generation. In Proceedings of the 3rd Workshop on Question Generation, pages 11-20, Carnegie Mellon Uni- versity, PA, 2010. Software available at http://www. ark.cs.cmu.edu/mheilman/questions/.","title":"Extracting Simplified Statements for Factual Question Generation","authors":"Smith ; Heilman, Michael Heilman, Noah Smith","year":"2010","venue":"Proceedings of the 3rd Workshop on Question Generation","doi":null,"url":"http://www.ark.cs.cmu.edu/mheilman/questions/","internal_url":null},{"position":11,"raw":"[Melli et al., 2005] Gabor Melli, Yang Wang, Yudong Liu, Mehdi M. Kashani, Zhongmin Shi, Baohua Gu, Anoop Sarkar, and Fred Popowich. Description of SQUASH, the SFU Question Answering Summary Handler for the DUC-2005 Summarization Task. In Proceedings of the Human Language Technology Conference and the Con- ference on Empirical Methods in Natural Language Pro- cessing Document Understanding Workshop, Vancouver, Canada, 2005.","title":"Description of SQUASH, the SFU Question Answering Summary Handler for the DUC-2005 Summarization Task","authors":"Gabor Melli, Yang Wang, Yudong Liu, M Mehdi, Zhongmin Kashani, Baohua Shi, Anoop Gu, Fred Sarkar, Popowich","year":"2005","venue":"Proceedings of the Human Language Technology Conference and the Conference on Empirical Methods in Natural Language Processing Document Understanding Workshop","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Palmer et al., 2005] Martha Palmer, Daniel Gildea, and Paul Kingsbury. The Proposition Bank: An Annotated Corpus of Semantic Roles. Computational Linguistics, 31(1):71-106, 2005.","title":"The Proposition Bank: An Annotated Corpus of Semantic Roles","authors":"Martha Palmer, Daniel Gildea, Paul Kingsbury","year":"2005","venue":"Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Pang et al., 2003] Bo Pang, Kevin Knight, and Daniel Marcu. Syntax-based Alignment of Multiple Translations: Extracting Paraphrases and Generating New Sentences. In Proceedings of the NAACL, pages 181-188, Edmonton, Canada, 2003.","title":"Syntax-based Alignment of Multiple Translations: Extracting Paraphrases and Generating New Sentences","authors":"Bo Pang, Kevin Knight, Daniel Marcu","year":"2003","venue":"Proceedings of the NAACL","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Shen and Lapata, 2007] Dan Shen and Mirella Lapata. Us- ing Semantic Roles to Improve Question Answering. In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Compu- tational Natural Language Learning (EMNLP-CoNLL), pages 12-21, Prague, Czech Republic, 2007.","title":"Using Semantic Roles to Improve Question Answering","authors":"Lapata ; Shen, Dan Shen, Mirella Lapata","year":"2007","venue":"Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Surdeanu et al., 2003] Mihai Surdeanu, Sanda Harabagiu, John Williams, and Paul Aarseth. Using Predicate- Argument Structures for Information Extraction. In Pro- ceedings of the Annual Meeting of the Association for Computational Linguistics, pages 8-15, Sapporo, Japan, 2003.","title":"Using Predicate-Argument Structures for Information Extraction","authors":"Mihai Surdeanu, Sanda Harabagiu, John Williams, Paul Aarseth","year":"2003","venue":"Proceedings of the Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Toutanova et al., 2005] Kristina Toutanova, Aria Haghighi, and Christopher Manning. Joint learning improves se- mantic role labeling. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL'05), pages 589-596, Ann Arbor, Michigan, June 2005.","title":"Joint learning improves semantic role labeling","authors":"Kristina Toutanova, Aria Haghighi, Christopher Manning","year":"2005","venue":"Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL'05)","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Woodsend and Lapata, 2011] Kristian Woodsend and Mirella Lapata. Learning to simplify sentences with quasi-synchronous grammar and integer programming. In Proceedings of the 2011 Conference on Empirical Meth- ods in Natural Language Processing, pages 409-420, Edinburgh, Scotland, UK., 2011. We used the Wikipedia revisions corpus, retrieved from http://homepages. inf.ed.ac.uk/kwoodsen/wiki.html.","title":"Learning to simplify sentences with quasi-synchronous grammar and integer programming","authors":"Lapata Woodsend, Kristian Woodsend, Mirella Lapata","year":"2011","venue":"Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing","doi":null,"url":"http://homepages.inf.ed.ac.uk/kwoodsen/wiki.html","internal_url":null},{"position":18,"raw":"[Woodsend and Lapata, 2012] Kristian Woodsend and Mirella Lapata. Multiple aspect summarization using integer linear programming. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Lan- guage Processing and Computational Natural Language Learning, pages 233-243, Jeju Island, Korea, July 2012.","title":"Multiple aspect summarization using integer linear programming","authors":"Kristian Woodsend, Mirella Lapata","year":"2012","venue":"Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Woodsend and Lapata, 2014] Kristian Woodsend and Mirella Lapata. Text rewriting improves semantic role labeling. Journal of Artificial Intelligence Research, 51:133-164, 2014.","title":"Text rewriting improves semantic role labeling","authors":"Lapata Woodsend, Kristian Woodsend, Mirella Lapata","year":"2014","venue":"Journal of Artificial Intelligence Research","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Wu and Fung, 2009] Dekai Wu and Pascale Fung. Semantic Roles for SMT: A Hybrid Two-Pass Model. In Proceed- ings of Human Language Technologies: The Annual Con- ference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers, pages 13-16, Boulder, Colorado, 2009.","title":"Semantic Roles for SMT: A Hybrid Two-Pass Model","authors":"Fung ; ] Dekai Wu, Pascale Wu, Fung","year":"2009","venue":"Proceedings of Human Language Technologies: The Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}