Abstract
This article makes an effort to improve Semantic Role Labeling (SRL) through learning generalized features. The SRL task is usually treated as a supervised problem. Therefore, a huge set of features are crucial to the performance of SRL systems. But these features often lack generalization powers when predicting an unseen argument. This article proposes a simple approach to relieve the issue. A strong intuition is that arguments occurring in similar syntactic positions are likely to bear the same semantic role, and, analogously, arguments that are lexically similar are likely to represent the same semantic role. Therefore, it will be informative to SRL if syntactic or lexical similar arguments can activate the same feature. Inspired by this, we embed the information of lexicalization and syntax into a feature vector for each argument and then use K-means to make clustering for all feature vectors of training set. For an unseen argument to be predicted, it will belong to the same cluster as its similar arguments of training set. Therefore, the clusters can be thought of as a kind of generalized feature. We evaluate our method on several benchmarks. The experimental results show that our approach can significantly improve the SRL performance.
- Collin F. Baker, Charles J. Fillmore, and John B. Lowe. 1998. The berkeley framenet project. In Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics (ACL’98). Google Scholar
Digital Library
- Antoine Bordes, Sumit Chopra, and Jason Weston. 2014. Question answering with subgraph embeddings. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP’14). Association for Computational Linguistics, 615--620.Google Scholar
Cross Ref
- Xavier Carreras, Lluís Màrquez, and Grzegorz Chrupała. 2004. Hierarchical recognition of propositional arguments with perceptrons. In HLT-NAACL 2004 Workshop: 8th Conference on Computational Natural Language Learning (CoNLL’04).Google Scholar
- Janara Christensen, Mausam, Stephen Soderland, and Oren Etzioni. 2010. Semantic role labeling for open information extraction. In Proceedings of the NAACL HLT 2010 1st International Workshop on Formalisms and Methodology for Learning by Reading. Google Scholar
Digital Library
- Ronan Collobert. 2011. Deep learning for efficient discriminative parsing. In Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS-11), Geoffrey J. Gordon and David B. Dunson (Eds.), Vol. 15. Journal of Machine Learning Research—Workshop and Conference Proceedings, 224--232.Google Scholar
- Ronan Collobert, Jason Weston, Léon Bottou, Michael Karlen, Koray Kavukcuoglu, and Pavel Kuksa. 2011. Natural language processing (almost) from scratch. J. Mach. Learn. Res. 12 (Nov. 2011), 2493--2537. Google Scholar
Digital Library
- Koen Deschacht and Marie-Francine Moens. 2009. Semi-supervised semantic role labeling using the latent words language model. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 21--29. Google Scholar
Digital Library
- Jacob Devlin, Rabih Zbib, Zhongqiang Huang, Thomas Lamar, Richard Schwartz, and John Makhoul. 2014. Fast and robust neural network joint models for statistical machine translation. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, 1370--1380.Google Scholar
Cross Ref
- Hagen Fürstenau and Mirella Lapata. 2009. Graph alignment for semi-supervised semantic role labeling. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 11--20. Google Scholar
Digital Library
- Daniel Gildea and Daniel Jurafsky. 2002. Automatic labeling for semantic roles. Comput. Linguist. 28, 3 (2002), 245--288. Google Scholar
Digital Library
- Daniel Gildea and Martha Palmer. 2002. The necessity of parsing for predicate argument recognition. In Proceedings of the Joint Conference of the 40th Annual Meeting of the ACL (ACL’02). Google Scholar
Digital Library
- Karl Moritz Hermann, Dipanjan Das, Jason Weston, and Kuzman Ganchev. 2014. Semantic frame identification with distributed word representations. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, 1448--1458.Google Scholar
Cross Ref
- Terry Koo, Xavier Carreras, and Michael Collins. 2008. Simple semi-supervised dependency parsing. In Proceedings of ACL-08: HLT. Association for Computational Linguistics, 595--603.Google Scholar
- Ding Liu and Daniel Gildea. 2010. Semantic role features for machine translation. In Proceedings of the 23rd International Conference on Computational Linguistics (COLING’10). Google Scholar
Digital Library
- Scott Miller, Jethran Guinness, and Alex Zamanian. 2004. Name tagging with word clusters and discriminative Training. In HLT-NAACL 2004: Main Proceedings, Daniel Marcu Susan Dumais and Salim Roukos (Eds.). Association for Computational Linguistics, 337--342. Google Scholar
Digital Library
- Jeff Mitchell and Mirella Lapata. 2010. Composition in distributional models of semantics. Cogn. Sci. 34, 8 (2010), 1388--1429. DOI:http://dx.doi.org/10.1111/j.1551-6709.2010.01106.xGoogle Scholar
Cross Ref
- Alessandro Moschitti, Daniele Pighin, and Roberto Basili. 2008. Tree kernels for semantic role labeling. Comput. Linguist. 34, 2 (June 2008), 193--224. DOI:http://dx.doi.org/10.1162/coli.2008.34.2.193 Google Scholar
Digital Library
- Srini Narayanan and Sanda Harabagiu. 2004. Question answering based on semantic structures. In Proceedings of the 17th International Conference on Computational Linguistics (COLING’04). Google Scholar
Digital Library
- Thien Huu Nguyen and Ralph Grishman. 2014. Employing word representations and regularization for domain adaptation of relation extraction. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Association for Computational Linguistics, 68--74.Google Scholar
Cross Ref
- Sameer Pradhan, Kadri Hacioglu, Valerie Krugler, Wayne Ward, James H. Martin, and Daniel Jurafsky. 2005. Support vector learning for semantic argument classification. Mach. Learn. 60, 1--3 (Sept. 2005), 11--39. DOI:http://dx.doi.org/10.1007/s10994-005-0912-2 Google Scholar
Digital Library
- Vasin Punyakanok, Dan Roth, Wen-tau Yih, and Dav Zimak. 2004. Semantic role labeling via integer linear programming inference. In Proceedings of the 20th International Conference on Computational Linguistics (COLING’04). DOI:http://dx.doi.org/10.3115/1220355.1220552 Google Scholar
Digital Library
- Michael Roth and Kristian Woodsend. 2014. Composition of word representations improves semantic role labelling. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics, 407--413.Google Scholar
Cross Ref
- Richard Socher, Brody Huval, Christopher D. Manning, and Andrew Y. Ng. 2012. Semantic compositionality through recursive matrix-vector spaces. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. Association for Computational Linguistics, 1201--1211. Google Scholar
Digital Library
- Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D. Manning, Andrew Ng, and Christopher Potts. 2013. Recursive deep models for semantic compositionality over a sentiment treebank. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 631--1642.Google Scholar
- Ang Sun, Ralph Grishman, and Satoshi Sekine. 2011. Semi-supervised relation extraction with large-scale word clustering. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, 521--529. Google Scholar
Digital Library
- Weiwei Sun, Zhifang Sui, Meng Wang, and Xin Wang. 2009. Chinese semantic role labeling with shallow parsing. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 1475--1483. Google Scholar
Digital Library
- Mihai Surdeanu, Sanda Harabagiu, John Williams, and Paul Aarseth. 2003. Using predicate-argument structures for information extraction. In Proceedings of the 41st Annual Meeting on Association for Computational Linguistics (ACL’03). DOI:http://dx.doi.org/10.3115/1075096.1075098 Google Scholar
Digital Library
- Mihai Surdeanu and Jordi Turmo. 2005. Semantic role labeling using complete syntactic analysis. In Proceedings of the Ninth Conference on Computational Natural Language Learning (CoNLL-2005). Association for Computational Linguistics, 221--224. Google Scholar
Digital Library
- Ivan Titov and Alexandre Klementiev. 2012. A bayesian approach to unsupervised semantic role induction. In Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics. Association for Computational Linguistics, Avignon, France, 12--22. Google Scholar
Digital Library
- Kristina Toutanova, Aria Haghighi, and Christopher Manning. 2005. Joint learning improves semantic role labeling. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL’05). Association for Computational Linguistics, Ann Arbor, MI, 589--596. DOI:http://dx.doi.org/10.3115/1219840.1219913 Google Scholar
Digital Library
- Kristina Toutanova, Aria Haghighi, and Christopher D. Manning. 2008. A global joint model for semantic role labeling. Comput. Linguist. 34, 2 (June 2008), 161--191. DOI:http://dx.doi.org/10.1162/coli.2008.34.2.161 Google Scholar
Digital Library
- Joseph Turian, Lev-Arie Ratinov, and Yoshua Bengio. 2010. Word representations: A simple and general method for semi-supervised learning. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Uppsala, Sweden, 384--394. Google Scholar
Digital Library
- Dekai Wu and Pascale Fung. 2009. Can semantic role labeling improve SMT?. In Proceedings of the 13th Annual Conference of European Association for Machine Translation (EAMT’09).Google Scholar
- Deyi Xiong, Min Zhang, and Haizhou Li. 2012. Modeling the translation of predicate-argument structure for SMT. In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (ACL’12). Google Scholar
Digital Library
- Nianwen Xue. 2008. Labeling chinese predicates with semantic roles. Comput. Linguist. 34, 2 (June 2008), 225--255. DOI:http://dx.doi.org/10.1162/coli.2008.34.2.225 Google Scholar
Digital Library
- Nianwen Xue and Martha Palmer. 2003. Annotating the propositions in the penn chinese treebank. In Proceedings of the Second SIGHAN Workshop on Chinese Language Processing. Association for Computational Linguistics, 47--54. DOI:http://dx.doi.org/10.3115/1119250.1119257 Google Scholar
Digital Library
- Nianwen Xue and Martha Palmer. 2004. Calibrating features for semantic role labeling. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’04).Google Scholar
- Haitong Yang, Yu Zhou, and Chengqing Zong. 2016. Bilingual semantic role labeling inference via dual decomposition. ACM Trans. Asian Low-Resour. Lang. Inf. Process. 15, 3, Article 15 (Jan. 2016), 21 pages. DOI:http://dx.doi.org/10.1145/2835493 Google Scholar
Digital Library
- Haitong Yang, Tao Zhuang, and Chengqing Zong. 2015. Domain adaptation for syntactic and semantic dependency parsing using deep belief networks. Transactions of the Association for Computational Linguistics 3 (2015), 271--282.Google Scholar
Cross Ref
- Haitong Yang and Chengqing Zong. 2014. Multi-predicate semantic role labeling. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP’14).Google Scholar
Cross Ref
- Feifei Zhai, Jiajun Zhang, Yu Zhou, and Chengqing Zong. 2012. Machine translation by modeling predicate-argument structure transformation. In Proceedings of the 23rd International Conference on Computational Linguistics (COLING’12).Google Scholar
- Feifei Zhai, Jiajun Zhang, Yu Zhou, and Chengqing Zong. 2013. Handling ambiguities of bilingual predicate-argument structures for statistical machine translation. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (ACL’13).Google Scholar
- Ying Zhang, Stephan Vogel, and Alex Waibel. 2004. Interpreting bleu/NIST scores: How much improvement do we need to have a better system?. In Proceedings of the 4th International Conference on Language Resources and Evaluation (LREC’04). 2051--2054.Google Scholar
- Tao Zhuang and Chengqing Zong. 2010a. Joint inference for bilingual semantic role labeling. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing (EMNLP’10). Google Scholar
Digital Library
- Tao Zhuang and Chengqing Zong. 2010b. A minimum error weighting combination strategy for chinese semantic role labeling. In Proceedings of the 23rd International Conference on Computational Linguistics (COLING’10). Google Scholar
Digital Library
Index Terms
Learning Generalized Features for Semantic Role Labeling
Recommendations
Multi-label learning based on label-specific features and local pairwise label correlation
Multi-label learning has drawn great attention in recent years. One of its tasks aims to build classification models for the problem where each instance associates with a set of labels. In order to exploit discriminative features for classification, ...
Transductive Multilabel Learning via Label Set Propagation
The problem of multilabel classification has attracted great interest in the last decade, where each instance can be assigned with a set of multiple class labels simultaneously. It has a wide variety of real-world applications, e.g., automatic image ...
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 ...






Comments