ABSTRACT
In this paper, we report experiments that explore learning of syntactic and semantic representations. First, we extend a state-of-the-art statistical parser to produce a richly annotated tree that identifies and labels nodes with semantic role labels as well as syntactic labels. Secondly, we explore rule-based and learning techniques to extract predicate-argument structures from this enriched output. The learning method is competitive with previous single-system proposals for semantic role labelling, yields the best reported precision, and produces a rich output. In combination with other high recall systems it yields an F-measure of 81%.
- Collins, Michael John. 1999. Head-driven statistical models for natural language parsing. Ph.D. thesis, University of Pennsylvania. Google ScholarDigital Library
- Ge, Ruifang and Raymond J. Mooney. 2005. A statistical semantic parser that integrates syntax and semantics. In Procs of CONLL-05, Ann Arbor, Michigan. Google ScholarDigital Library
- Gildea, Daniel and Daniel Jurafsky. 2002. Automatic labeling of semantic roles. Computational Linguistics, 28(3):245--288. Google ScholarDigital Library
- Haghighi, Aria, Kristina Toutanova, and Christopher Manning. 2005. A joint model for semantic role labeling. In Procs of CoNLL-2005, pages 173--176, Ann Arbor, Michigan. Google ScholarDigital Library
- Henderson, Jamie. 2003. Inducing history representations for broad-coverage statistical parsing. In Procs of NAACL-HLT'03, pages 103--110, Edmonton, Canada. Google ScholarDigital Library
- Henderson, James, Paola Merlo, Gabriele Musillo and Ivan Titov. 2008. A latent variable model of synchronous parsing for syntactic and semantic dependencies. In Procs of CoNLL'08 Shared Task, Manchester, UK. Google ScholarDigital Library
- Jensen, Finn V. 2001. Bayesian networks and decision graphs. Springer Verlag. Google ScholarDigital Library
- Joachims, Thorsten. 1999. Making large-scale svm learning practical. In Schlkopf, B., C. Burges, and A. Smola, editors, Advances in Kernel Methods - Support Vector Learning. MIT Press. Google ScholarDigital Library
- Johansson, Richard and Pierre Nugues. 2005. Sparse bayesian classification of predicate arguments. In Procs of CoNLL-2005, pages 177--180, Ann Arbor, Michigan. Google ScholarDigital Library
- Levin, Lori. 1986. Operations on lexical form: unaccusative rules in Germanic languages. Ph.D. thesis, Massachusetts Institute of Technology.Google Scholar
- Liu, Ting, Wanxiang Che, Sheng Li, Yuxuan Hu, and Huaijun Liu. 2005. Semantic role labeling system using maximum entropy classifier. In Procs of CoNLL-2005, pages 189--192, Ann Arbor, Michigan. Google ScholarDigital Library
- Marcus, Mitch, Beatrice Santorini, and M. A. Marcinkiewicz. 1993. Building a large annotated corpus of English: the Penn Treebank. Computational Linguistics, 19:313--330. Google ScholarDigital Library
- Miller, S., H. Fox, L. Ramshaw, and R. Weischedel. 2000. A novel use of statistical parsing to extract information from text. In Procs of NAACL 2000. Google ScholarDigital Library
- Moschitti, Alessandro, Ana-Maria Giuglea, Bonaventura Coppola, and Roberto Basili. 2005. Hierarchical semantic role labeling. In Procs of CoNLL-2005, pages 201--204, Ann Arbor, Michigan. Google ScholarDigital Library
- Musillo, Gabriele and Paola Merlo. 2005. Lexical and structural biases for function parsing. In Procs of IWPT'05, pages 83--92, Vancouver, British Columbia, October. Google ScholarDigital Library
- Musillo, Gabriele and Paola Merlo. 2006. Accurate semantic parsing of the proposition bank. In Procs of NAACL'06, New York, NY. Google ScholarDigital Library
- Ozgencil, Necati Ercan and Nancy McCracken. 2005. Semantic role labeling using libSVM. In Procs of CoNLL-2005, pages 205--208, Ann Arbor, Michigan, June. Google ScholarDigital Library
- Palmer, Martha, Daniel Gildea, and Paul Kingsbury. 2005. The Proposition Bank: An annotated corpus of semantic roles. Computational Linguistics, 31:71--105. Google ScholarDigital Library
- Punyakanok, Vasin, Peter Koomen, Dan Roth, and Wen tau Yih. 2005. Generalized inference with multiple semantic role labeling systems. In Procs of CoNLL-2005, Ann Arbor, MI USA. Google ScholarDigital Library
- Rizzi, Luigi. 1990. Relativized minimality. MIT Press, Cambridge, MA.Google Scholar
- Surdeanu, Mihai and Jordi Turmo. 2005. Semantic role labeling using complete syntactic analysis. In Procs of CoNLL'05, Ann Arbor, Michigan. Google ScholarDigital Library
- Titov, Ivan and James Henderson. 2007. Constituent parsing with Incremental Sigmoid Belief Networks. In Procs of ACL'07, pages 632--639, Prague, Czech Republic.Google Scholar
- Wong, Yuk Wah and Raymond Mooney. 2007. Learning synchronous grammars for semantic parsing with lambda calculus. In Procs of ACL'07, pages 960--967, Prague, Czech Republic.Google Scholar
- Yi, Szu-ting and Martha Palmer. 2005. The integration of semantic parsing and semantic role labelling. In Procs of CoNLL'05, Ann Arbor, Michigan. Google ScholarDigital Library
- Zettlemoyer, Luke and Michael Collins. 2007. Online learning of relaxed CCG grammars for parsing to logical form. In Procs of EMNLP-CoNLL'07, pages 678--687.Google Scholar
Index Terms
- Semantic parsing for high-precision semantic role labelling
Recommendations
The integration of syntactic parsing and semantic role labeling
CONLL '05: Proceedings of the Ninth Conference on Computational Natural Language LearningThis paper describes a system for the CoNLL-2005 Shared Task on Semantic Role Labeling. We trained two parsers with the training corpus in which the semantic argument information is attached to the constituent labels, we then used the resulting parse ...
Chinese semantic role labeling with shallow parsing
EMNLP '09: Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 3 - Volume 3Most existing systems for Chinese Semantic Role Labeling (SRL) make use of full syntactic parses. In this paper, we evaluate SRL methods that take partial parses as inputs. We first extend the study on Chinese shallow parsing presented in (Chen et al., ...
Comments