Abstract
Null instantiation has attracted much attention recently. In this paper, we focus on gap filling of definite null instantiation, namely, finding an antecedent for a given definite null instantiation from context. Most of the approaches for solving this problem use syntactic features, and only few consider semantic features. Moreover, these approaches only take the noun, noun phrase and pronoun as candidate words, so the coverage of antecedent is narrow. In this paper, we use new features of words and frame except traditional features, and create a rule to build candidate words set. At last, we choose the best candidate words set and feature template based on employing standard annotated corpus, then use them to deal with corpus of NIs only in task SemEval-10 Task 10. According to the experimental results, our approach achieves a better performance than existing approaches.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Fillmore, C.J., Johnson, R., Petruck, M.R.L.: Background to FrameNet. International Journal of Lexicography 16(3), 235 (2003)
Fillmore, C.J., Ruppenhofer, J., Baker, C.F.: Framenet and representing the link between semantic and syntactic relations. In: Huang, C., Lenders, W. (eds.) Frontiers in Linguistics. Language and Linguistics Monograph Series B, vol. I, pp. 19–59. Institute of Linguistics, Academia Sinica, Taipei (2004)
Ruppenhofer, J., Sporleder, C., Morante, R., Baker, C., Palmer, M.: SemEval-2010 Task 10: Linking Events and Their Participants in Discourse. In: Proc. of the HLT-NAACL Workshop on Semantic Evaluations: Recent Achievements and Future Directions, Boulder, Colorado (2009)
Tonelli, S., Delmonte, R.: VENSES++:Adapting a deep semantic processing system to the identification of null instantiations. In: Proceedings of the 5th International Workshop on Semantic Evaluation, ACL 2010, Uppsala, Sweden, pp. 296–299 (2010)
Liu, H., Singh, P.: ConceptNet: a practical commonsense reasoning toolkit (2004), http://web.media.mit.edu/~push/ConceptNet.pdf
Chen, D., Schneider, N., Das, D., Smith, N.A.: SEMATOR: Frame Argument Resolution with Log-Linear Models. In: Proceedings of the 5th International Workshop on Semantic Evaluation, ACL 2010, Uppsala, Sweden, pp. 264–267 (2010)
Gorinski, P., Ruppenhofer, J., Sporleder, C.: Towards weakly supervised resolution of null instantiations. In: Proceedings of the 10th International Conference on Computational Semantics (IWCS 2013)–Long Papers, pp. 119–130 (2013)
Silberer, C., Frank, A.: Casting implicit role linking as an anaphora resolution task. In: Proceedings of the First Joint Conference on Lexical and Computational Semantics: Proceedings of the Main Conference and the Shared Task: Proceedings of the Sixth International Workshop on Semantic Evaluation, vol. 1, 2, pp. 1–10. Association for Computational Linguistics (2012)
Gerber, M., Chai, J.Y.: Beyond nombank: a study of implicit arguments for nominal predicates. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, ACL 2010, pp. 1583–1592. Association for Computational Linguistics, Stroudsburg (2010)
Gerber, M., Chai, J.Y.: Semantic role labeling of implicit arguments for nominal predicates. Computational Linguistics 38(4), 755–798 (2012)
Le, Z.: Maximum entropy modeling toolkit for python and c++ (2005), http://homepages.inf.ed.ac.uk/s0450736/maxent-toolkit.html
Lei, Z., Wang, N., Li, R., Wang, Z.: Definite Null Instantiation Recognizing in FrameNet. Journal of Chinese Information 27(3), 107–112 (2013)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wang, N., Li, R., Lei, Z., Wang, Z., Jin, J. (2013). Document Oriented Gap Filling of Definite Null Instantiation in FrameNet. In: Sun, M., Zhang, M., Lin, D., Wang, H. (eds) Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data. NLP-NABD CCL 2013 2013. Lecture Notes in Computer Science(), vol 8202. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-41491-6_9
Download citation
DOI: https://doi.org/10.1007/978-3-642-41491-6_9
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-41490-9
Online ISBN: 978-3-642-41491-6
eBook Packages: Computer ScienceComputer Science (R0)