Abstract
The high cardinality of antecedent candidates is one of the major reasons which make zero pronoun resolution difficult. To improve performance, it is necessary to reduce this cardinality before defining the features to choose the most plausible antecedent. This paper proposes a two-step method for intra-sentential zero pronoun resolution. First, the clause which contain the antecedent for a given zero pronoun is determined using structural relationships between clauses. Then, the antecedent of the zero pronoun is chosen from the noun phrases within the identified clause. The cardinality of candidates reduces to the number of antecedent candidates present in clauses. Our experimental results show that the proposed method outperforms other methods without the first step, no matter what features are used to identify antecedents.
Keywords
- zero pronoun
- candidate cardinality
- hierarchy of linguistic units
- relationship between clauses
This is a preview of subscription content, access via your institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Iida, R., Poesio, M.: A cross-lingual ilp solution to zero anaphora resolution. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pp. 804–813 (2011)
Ferrández, A., Peral, J.: A computational approach to zero-pronouns in Spanish. In: Proceedings of the 38th Annual Meeting of the Association for Computational Linguistics, pp. 166–172 (2000)
Zhao, S., Ng, H.T.: Identification and resolution of Chinese zero pronouns: A machine learning approach. In: Proceedings of the 2007 Joint Conference on EMNLP and CNLL, pp. 541–550 (2007)
Iida, R., Inui, K., Matsumoto, Y.: Zero-anaphora resolution by learning rich syntactic pattern features. ACM Transactions on Asian Language Information Processing 6(4), 1–22 (2007)
Kong, F., Zhou, G.: A tree kernel-based unified framework for Chinese zero anaphora resolution. In: Proceedings of EMNLP, pp. 882–891 (October 2010)
Collins, M., Duffy, N.: Convolution kernels for natural language. In: Proceedings of Neural Information Processing Systems, pp. 625–632 (2001)
Poesio, M., Stevenson, R., Eugenio, B.D., Hitzeman, J.: Centering: A parametric theory and its instantiations. Computational Linguistics 30(3), 309–363 (2004)
Sakurai, Y.: Centering inJapanese: How to rank forward-looking centers in a complex sentence. In: Proceedings of the 22nd Northwest Linguistic Conference, pp. 243–256 (2006)
Wiesemann, L.M.: The function of Spanish and English relative clauses in discourse and their segmentation in Centering Theory. PhD thesis, Department of Linguistics, Simon Fraser University (2009)
Hu, Q.: A Corpus-based Study on Zero Anaphora Resolution in Chinese Discours. PhD thesis, Department of Chinese, Translation and Linguistics, City University of Hong Kong (2008)
Abdul-Mageed, M.: Automatic detection of Arabic non-anaphoric pronouns for improving anaphora resolution. ACM Transactions on Asian Language Information Processing 10(1) (2011)
Amit, Y., Fink, M., Srebro, N., Ulman, S.: Uncovering shared structures in multiclass classification. In: Proceedings of the 24th ICML (2007)
Zhang, M., Zhang, J., Su, J.: Exploring syntactic features for relation extraction using a convolution tree kernel. In: Proceedings of the HLT/NAACL, pp. 288–295 (2006)
Yang, X., Su, J., Tan, C.: Kernel-based pronoun resolution with structured syntactic knowledge. In: Proceedings of COLING-ACL, pp. 41–48 (2006)
Han, N.R.: Korean Zero Pronous: Analysis and Resolution. PhD thesis, Department of Linguistics at the University of Pennsylvania (2006)
Joachims, T.: Making large-Scale SVM Learning Practical. In: Advances in Kernel Methods - Support Vector Learning. MIT Press (1999)
Leffa, V.J.: Clause processing in complex sentences. In: Proceedings of the 1st International Conference on Language Resources and Evaluation, pp. 937–943 (1998)
Zhou, G., Kong, F., Zhu, Q.: Context-sensitive convolution tree kernel for pronoun resolution. In: Proceedings of the IJCNLP, pp. 25–31 (2008)
Moschitti, A.: Making tree kernels practical for natural language learning. In: Proceedings of the 11th International Conference on European Association for Computational Linguistics, pp. 113–120 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kim, KS., Choi, SJ., Park, SB., Lee, SJ. (2012). A Two-Step Zero Pronoun Resolution by Reducing Candidate Cardinality. In: Anthony, P., Ishizuka, M., Lukose, D. (eds) PRICAI 2012: Trends in Artificial Intelligence. PRICAI 2012. Lecture Notes in Computer Science(), vol 7458. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-32695-0_19
Download citation
DOI: https://doi.org/10.1007/978-3-642-32695-0_19
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-32694-3
Online ISBN: 978-3-642-32695-0
eBook Packages: Computer ScienceComputer Science (R0)
