Abstract
The latest developments in neural semantic role labeling (SRL) have shown great performance improvements with both the dependency and span formalism/styles. Although the two styles share many similarities in linguistic meaning and computation, most previous studies focus on a single style. In this article, we define a new cross-style semantic role label convention and propose a new cross-style joint optimization model designed around the most basic linguistic meaning of a semantic role. Our work provides a solution to make the results of the two styles more comparable and allowing both formalisms of SRL to benefit from their natural connections in both linguistics and computation. Our model learns a general semantic argument structure and is capable of outputting in either style. Additionally, we propose a syntax-aided method to uniformly enhance the learning of both dependency and span representations. Experiments show that the proposed methods are effective on both span and dependency SRL benchmarks.
- [1] . 2018. A full end-to-end semantic role labeler, syntactic-agnostic over syntactic-aware?. In Proceedings of the 27th International Conference on Computational Linguistics. Association for Computational Linguistics, Santa Fe, NM, 2753–2765. https://www.aclweb.org/anthology/C18-1233.Google Scholar
- [2] . 2004. Introduction to the CoNLL-2004 shared task: Semantic role labeling. In Proceedings of the 8th Conference on Computational Natural Language Learning (CoNLL’04) at HLT-NAACL 2004. Association for Computational Linguistics, Boston, MA, 89–97. https://www.aclweb.org/anthology/W04-2412.Google Scholar
- [3] . 2005. Introduction to the CoNLL-2005 shared task: Semantic role labeling. In Proceedings of the 9th Conference on Computational Natural Language Learning (CoNLL’05). Association for Computational Linguistics, Ann Arbor, MI, 152–164. https://www.aclweb.org/anthology/W05-0620.Google Scholar
Cross Ref
- [4] . 1993. Lectures on Government and Binding: The Pisa Lectures. Walter de Gruyter.Google Scholar
Cross Ref
- [5] . 2003. Head-driven statistical models for natural language parsing. Computational Linguistics 29, 4 (2003), 589–637. https://doi.org/10.1162/089120103322753356Google Scholar
Digital Library
- [6] . 2006. Generating typed dependency parses from phrase structure parses. In Proceedings of the 5th International Conference on Language Resources and Evaluation (LREC’06). European Language Resources Association (ELRA), Genoa, Italy. http://www.lrec-conf.org/proceedings/lrec2006/pdf/440_pdf.pdf.Google Scholar
- [7] . 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In 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). Association for Computational Linguistics, Minneapolis, MN, 4171–4186. https://doi.org/10.18653/v1/N19-1423Google Scholar
- [8] . 2017. Deep biaffine attention for neural dependency parsing. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. OpenReview.net. https://openreview.net/forum?id=Hk95PK9le.Google Scholar
- [9] . 2015. Semantic role labeling with neural network factors. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Lisbon, Portugal, 960–970. https://doi.org/10.18653/v1/D15-1112Google Scholar
Cross Ref
- [10] . 1979. Brown corpus manual: Manual of information to accompany a standard corpus of present-day edited American English for use with digital computers. Brown University, Providence, Rhode Island, USA.Google Scholar
- [11] . 2009. The CoNLL-2009 shared task: Syntactic and semantic dependencies in multiple languages. In Proceedings of the 13th Conference on Computational Natural Language Learning (Co’09): Shared Task. Association for Computational Linguistics, Boulder, CO, 1–18. https://aclanthology.org/W09-1201.Google Scholar
Cross Ref
- [12] . 2018. Jointly predicting predicates and arguments in neural semantic role labeling. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Association for Computational Linguistics, Melbourne, Australia, 364–369. https://doi.org/10.18653/v1/P18-2058Google Scholar
Cross Ref
- [13] . 2017. Deep semantic role labeling: What works and what’s next. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Vancouver, Canada, 473–483. https://doi.org/10.18653/v1/P17-1044Google Scholar
Cross Ref
- [14] . 2018. Syntax for semantic role labeling, to be, or not to be. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Melbourne, Australia, 2061–2071. https://doi.org/10.18653/v1/P18-1192Google Scholar
Cross Ref
- [15] . 2007. Extended constituent-to-dependency conversion for English. In Proceedings of the 16th Nordic Conference of Computational Linguistics (NODALIDA’07). University of Tartu, Estonia, Tartu, Estonia, 105–112. https://www.aclweb.org/anthology/W07-2416.Google Scholar
- [16] . 2008. Dependency-based syntactic–semantic analysis with PropBank and NomBank. In CoNLL 2008: Proceedings of the 12th Conference on Computational Natural Language Learning. Coling 2008 Organizing Committee, Manchester, England, 183–187. https://www.aclweb.org/anthology/W08-2123.Google Scholar
Cross Ref
- [17] . 2018. Constituency parsing with a self-attentive encoder. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Melbourne, Australia, 2676–2686. https://doi.org/10.18653/v1/P18-1249Google Scholar
Cross Ref
- [18] . 2018. A unified syntax-aware framework for semantic role labeling. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Brussels, Belgium, 2401–2411. https://doi.org/10.18653/v1/D18-1262Google Scholar
Cross Ref
- [19] . 2019. Dependency or span, end-to-end uniform semantic role labeling. In 33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Innovative Applications of Artificial Intelligence Conference, IAAI 2019, 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019, Honolulu, Hawaii, January 27 - February 1, 2019. AAAI Press, 6730–6737. https://doi.org/10.1609/aaai.v33i01.33016730Google Scholar
- [20] . 1994. Natural language parsing as statistical pattern recognition. CoRR abs/cmp-lg/9405009 (1994).
arXiv:cmp-lg/9405009 http://arxiv.org/abs/cmp-lg/9405009.Google Scholar - [21] . 2017. A simple and accurate syntax-agnostic neural model for dependency-based semantic role labeling. In Proceedings of the 21st Conference on Computational Natural Language Learning (Co’17). Association for Computational Linguistics, Vancouver, Canada, 411–420. https://doi.org/10.18653/v1/K17-1041Google Scholar
Cross Ref
- [22] . 2017. Encoding sentences with graph convolutional networks for semantic role labeling. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Copenhagen, Denmark, 1506–1515. https://doi.org/10.18653/v1/D17-1159Google Scholar
Cross Ref
- [23] . 1993. Building a large annotated corpus of English: The Penn Treebank. Computational Linguistics 19, 2 (1993), 313–330. https://www.aclweb.org/anthology/J93-2004.Google Scholar
Digital Library
- [24] . 2004. The NomBank project: An interim report. In Proceedings of the Workshop Frontiers in Corpus Annotation at HLT-NAACL 2004. Association for Computational Linguistics, Boston, MA, 24–31. https://aclanthology.org/W04-2705.Google Scholar
- [25] . 2005. The proposition bank: An annotated corpus of semantic roles. Computational Linguistics 31, 1 (2005), 71–106. https://doi.org/10.1162/0891201053630264Google Scholar
Digital Library
- [26] . 2018. Learning joint semantic parsers from disjoint data. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). Association for Computational Linguistics, New Orleans, LA, 1492–1502. https://doi.org/10.18653/v1/N18-1135Google Scholar
Cross Ref
- [27] . 2014. Glove: Global vectors for word representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP’14). Association for Computational Linguistics, Doha, Qatar, 1532–1543. https://doi.org/10.3115/v1/D14-1162Google Scholar
Cross Ref
- [28] . 2018. Deep contextualized word representations. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). Association for Computational Linguistics, New Orleans, LA, 2227–2237. https://doi.org/10.18653/v1/N18-1202Google Scholar
Cross Ref
- [29] . 2005. Semantic role labeling using different syntactic views. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL’05). Association for Computational Linguistics, Ann Arbor, M, 581–588. https://doi.org/10.3115/1219840.1219912Google Scholar
Digital Library
- [30] . 2005. The necessity of syntactic parsing for semantic role labeling. In Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence (IJCAI-05), Edinburgh, Scotland, UK, July 30 - August 5, 2005, and (Eds.). Professional Book Center, 1117–1123. http://ijcai.org/Proceedings/05/Papers/1672.pdf.Google Scholar
- [31] . 2008. The importance of syntactic parsing and inference in semantic role labeling. Computational Linguistics 34, 2 (2008), 257–287. https://doi.org/10.1162/coli.2008.34.2.257Google Scholar
Digital Library
- [32] . 2016. Neural semantic role labeling with dependency path embeddings. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Berlin, Germany, 1192–1202. https://doi.org/10.18653/v1/P16-1113Google Scholar
Cross Ref
- [33] . 2018. Linguistically-informed self-attention for semantic role labeling. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Brussels, Belgium, 5027–5038. https://doi.org/10.18653/v1/D18-1548Google Scholar
Cross Ref
- [34] . 2008. The CoNLL 2008 shared task on joint parsing of syntactic and semantic dependencies. In CoNLL 2008: Proceedings of the12th Conference on Computational Natural Language Learning. Coling 2008 Organizing Committee, Manchester, England, 159–177. https://aclanthology.org/W08-2121.Google Scholar
Cross Ref
- [35] . 2004. Calibrating features for semantic role labeling. In Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Barcelona, Spain, 88–94. https://www.aclweb.org/anthology/W04-3212.Google Scholar
- [36] . 2003. Statistical dependency analysis with support vector machines. In Proceedings of the 8th International Conference on Parsing Technologies. Nancy, France, 195–206. https://www.aclweb.org/anthology/W03-3023.Google Scholar
- [37] . 2015. End-to-end learning of semantic role labeling using recurrent neural networks. In 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). Association for Computational Linguistics, Beijing, China, 1127–1137. https://doi.org/10.3115/v1/P15-1109Google Scholar
Cross Ref
Index Terms
Dependency and Span, Cross-Style Semantic Role Labeling on PropBank and NomBank
Recommendations
Dependency-based semantic role labeling of PropBank
EMNLP '08: Proceedings of the Conference on Empirical Methods in Natural Language ProcessingWe present a PropBank semantic role labeling system for English that is integrated with a dependency parser. To tackle the problem of joint syntactic--semantic analysis, the system relies on a syntactic and a semantic subcomponent. The syntactic model ...
Dependency-based semantic role labeling using sequence labeling with a structural SVM
Semantic Role Labeling (SRL) systems aim at determining the semantic role labels of the arguments of the predicates in natural language text. SRL systems can usually be built to work upon the result of constitient analysis (constituent-based), or ...
Semantic Role Labeling of NomBank: a maximum entropy approach
EMNLP '06: Proceedings of the 2006 Conference on Empirical Methods in Natural Language ProcessingThis paper describes our attempt at NomBank-based automatic Semantic Role Labeling (SRL). NomBank is a project at New York University to annotate the argument structures for common nouns in the Penn Treebank II corpus. We treat the NomBank SRL task as a ...






Comments