Fast Semantic Role Labeling for Chinese Based on Semantic Chunking

  • Weiwei Ding
  • Baobao Chang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5459)

Abstract

Recently, with the development of Chinese semantically annotated corpora, e.g. the Chinese Proposition Bank, the Chinese semantic role labeling (SRL) has been boosted. However, the Chinese SRL researchers now focus on the transplant of existing statistical machine learning methods which have been proven to be effective on English. In this paper, we have established a semantic chunking based method which is different from the traditional ones. Semantic chunking is named because of its similarity with syntactic chunking. The difference is that semantic chunking is used to identify the semantic chunks, i.e. the semantic roles. Based on semantic chunking, the process of SRL is changed from “parsing – semantic role identification – semantic role classification”, to “semantic chunk identification – semantic chunk classification”. With the elimination of the parsing stage, the SRL task can get rid of the dependency on parsing, which is the bottleneck both of speed and precision. The experiments have shown that the semantic chunking based method outperforms previously best-reported results on Chinese SRL and saves a large amount of time.

Keywords

semantic chunking Chinese semantic role labeling 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Gildea, D., Jurafsky, D.: Automatic labeling of semantic roles. Computational Linguistics 28(3), 245–288 (2002)CrossRefGoogle Scholar
  2. 2.
    Narayanan, S., Harabagiu, S.: Question answering based on semantic structures. In: The 20th International Conference on Computational Linguistics, Geneva, Switzerland (2004)Google Scholar
  3. 3.
    Boas, H.C.: Bilingual FrameNet dictionaries for machine translation. In: The International Conference on Language Resources and Evaluation, Las Palmas, Spain (2002)Google Scholar
  4. 4.
    Carreras, X., Màrquez, L.: Introduction to the conll-2004 shared task: Semantic role labeling. In: The Eighth Conference on Natural Language Learning, Boston, Massachusetts, USA (2004)Google Scholar
  5. 5.
    Carreras, X., Màrquez, L.: Introduction to the conll-2005 shared task: Semantic role labeling. In: The Nineth Conference on Natural Language Learning, Ann Arbor, Michigan, USA (2005)Google Scholar
  6. 6.
    Sun, H., Jurafsky, D.: Shallow Semantic Parsing of Chinese. In: The Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, Boston, Massachusetts, USA (2004)Google Scholar
  7. 7.
    Xue, N., Palmer, M.: Automatic semantic role labeling for Chinese verbs. In: The 19th International Joint Conference on Artificial Intelligence, Edinburgh, Scotland (2005)Google Scholar
  8. 8.
    Xue, N.: Labeling Chinese predicates with semantic roles. Computational linguistics 34(2), 225–255 (2008)CrossRefGoogle Scholar
  9. 9.
    Xue, N., Palmer, M.: Annotating the Propositions in the Penn Chinese Treebank. In: The 2nd SIGHAN Workshop on Chinese Language Processing, Sapporo, Japan (2003)Google Scholar
  10. 10.
    Xue, N., Xia, F., Chiou, F., Palmer, M.: The Penn Chinese TreeBank: Phrase Structure Annotation of a Large Corpus. Natural Language Engineering 11(2), 207–238 (2005)CrossRefGoogle Scholar
  11. 11.
    Hacioglu, K., Ward, W.: Target word detection and semantic role chunking using support vector machines. In: The Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, Edmonton, Canada (2003)Google Scholar
  12. 12.
    Wang, R., Chi, Z., Wang, X., Wu, T.: An algorithm for semantic chunk identification of Chinese sentences. In: The Tenth IASTED International Conference on Intelligent Systems and Control, Cambridge, Massachusetts, USA (2007)Google Scholar
  13. 13.
    Ramshaw, L.A., Marcus, M.P.: Text chunking using transformation-based learning. In: The 3rd Workshop on Very Large Corpora, Cambridge, Massachusetts, USA (2005)Google Scholar
  14. 14.
    Sang, E., Kim, T., Veenstra, J.: Representing text chunks. In: The 38th Annual Meeting of the Association for Computational Linguistics, Hong Kong, China (1999)Google Scholar
  15. 15.
    Uchimoto, K., Ma, Q., Murata, M., Ozaku, H., Isahara, H.: Named Entity Extraction Based on A Maximum Entropy Model and Transformation Rules. In: The 38th Annual Meeting of the Association for Computational Linguistics, Hong Kong, China (2000)Google Scholar
  16. 16.
    Kudo, T., Matsumoto, Y.: Chunking with Support Vector Machines. In: Second Meeting of North American Chapter of the Association for Computational Linguistics, Pittsburgh, USA (2001)Google Scholar
  17. 17.
    Lafferty, J., McCallum, A., Pereira, F.: Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data. In: The 18th International Conference on Machine Learning, Williamstown, MA, USA (2001)Google Scholar
  18. 18.
    Wang, H., Zhan, W., Yu, S.: The Specification of The Semantic Knowledge-base of Contemporary Chinese. Journal of Chinese Language and Computing 13(2), 159–176 (2003)Google Scholar
  19. 19.
    Collins, M.: Head-Driven Statistical Models for Natural Language Parsing. Pennsylvania University (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Weiwei Ding
    • 1
  • Baobao Chang
    • 1
  1. 1.Institute of Computational LinguisticsPeking UniversityBeijingChina

Personalised recommendations