Learning to predict case markers in Japanese

ABSTRACT

Japanese case markers, which indicate the grammatical relation of the complement NP to the predicate, often pose challenges to the generation of Japanese text, be it done by a foreign language learner, or by a machine translation (MT) system. In this paper, we describe the task of predicting Japanese case markers and propose machine learning methods for solving it in two settings: (i) monolingual, when given information only from the Japanese sentence; and (ii) bilingual, when also given information from a corresponding English source sentence in an MT context. We formulate the task after the well-studied task of English semantic role labelling, and explore features from a syntactic dependency structure of the sentence. For the monolingual task, we evaluated our models on the Kyoto Corpus and achieved over 84% accuracy in assigning correct case markers for each phrase. For the bilingual task, we achieved an accuracy of 92% per phrase using a bilingual dataset from a technical domain. We show that in both settings, features that exploit dependency information, whether derived from gold-standard annotations or automatically assigned, contribute significantly to the prediction of case markers.

References

1. Baldwin, T. 2004. Making Sense of Japanese Relative Clause Constructions, In Proceedings of the 2nd Workshop on Text Meaning and Interpretation.
2. Blaheta, D. and E. Charniak. 2000. Assigning function tags to parsed text. In Proceedings of NAACL, pp.234--240.
3. Carreras, X. and L. Màrquez. 2005. Introduction to the CoNLL-2005 Shared Task: Semantic Role Labeling. In Proceedings of CoNLL-2005.
4. Clarkson, P. R. and R. Rosenfeld. 1997. Statistical Language Modeling Using the CMU-Cambridge Toolkit. In Proceedings of ESCA Eurospeech, pp. 2007--2010.
5. Collins, M. 2000. Discriminative reranking for natural language parsing. In Proceedings of ICML.
6. Gamon, M., E. Ringger, S. Corston-Oliver and R. Moore. 2002. Machine-learned Context for Linguistic Operations in German Sentence Realization. In Proceeding of ACL.
7. Gildea, D. and D. Jurafsky. 2002. Automatic Labeling of Semantic Roles. In Computational Linguistics 28(3): 245--288.
8. Hacioglu, K. 2004. Semantic Role Labeling using Dependency Trees. In Proceedings of COLING 2004.
9. Kawahara, D., N. Kaji and S. Kurohashi. 2000. Japanese Case Structure Analysis by Unsupervised Construction of a Case Frame Dictionary. In Proceedings of COLING, pp. 432--438.
10. Kurohashi, S. and M. Nagao. 1997. Kyoto University Text Corpus Project. In Proceedings of ANLP, pp.115--118.
11. Masuoka, T. and Y. Takubo. 1992. Kiso Nihongo Bunpou (Fundamental Japanese grammar), revised version. Kuroshio Shuppan, Tokyo.
12. Murata, M., and H. Isahara. 2005. Japanese Case Analysis Based on Machine Learning Method that Uses Borrowed Supervised Data. In Proceedings of IEEE NLP-KE-2005, pp.774--779.
13. Och, F. J. and H. Ney. 2000. Improved statistical alignment models. In Proceedings of ACL: pp.440--447.
14. Palmer, M., D. Gildea and P. Kingsbury. 2005. The Proposition Bank: An Annotated Corpus of Semantic Roles. In Computational Linguistics 31(1).
15. Pradhan, S., W. Ward, K. Hacioglu, L. Martin, D. Jurafsky. 2004. Shallow Semantic Parsing Using Support Vector Machines. In Proceedings of HLT/NAACL.
16. Quirk, C., A. Menezes and C. Cherry. 2005. Dependency Tree Translation: Syntactically Informed Phrasal SMT. In Proceedings of ACL.
17. Teramura, H. 1991. Nihongo-no shintakusu-toimi (Japanese syntax and meaning). Volume III. Kuroshio Shuppan, Tokyo.
18. Toutanova, K., A. Haghighi and C. D. Manning. 2005. Joint Learning Improves Semantic Role Labeling. In Proceeding of ACL, pp.589--596.
19. Uchimoto, K., S. Sekine and H. Isahara. 2002. Text Generation from Keywords. In Proceedings of COLING 2002, pp.1037--1043.

• Applied computing

  • Arts and humanities

• Computing methodologies

  • Artificial intelligence

• Hardware

  • Power and energy

    • Power estimation and optimization