Abstract
There are a large number of expression forms and semantic information in natural language, which contain fake, speculative, and fuzzy statements. Identifying event factuality is vital to various natural language applications, such as information extraction and knowledge base population. Most of existing methods for Chinese event factuality detection adopt shallow lexical and syntactic features to determine the factuality of target event via end-to-end classification models. Although such methods are easy to implement, they ignore the linguistic features related to event factuality, which limits the performances on this task. On this basis, we introduce three kinds of linguistic features to represent event factuality, including factuality cue, event polarity, and tense. Then, we employ a CNN-based feature encoder to capture their latent feature representations automatically. Finally, we integrate three kinds of features with word embeddings to identify the factuality label of target event. The experimental results show that our method achieves 94.15% of accuracy, with 12.34% of improvement on the state-of-the-art. In addition, we also demonstrate and analyze the effectiveness of three linguistic features for Chinese event factuality detection.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
FactBank annotation guideline [1] to classify and define the categories of event factuality.
- 2.
- 3.
- 4.
In this paper, five types of event factuality are positive samples, so the value of P, R, F1 are equal when calculated on Micro-Ave.
References
Sauri, R., Verhagen, M., Pustejovsky, J.: Annotating and recognizing event modality in text. In: Proceedings of 19th International FLAIRS Conference (2006)
Schütze, H., Adel, H.: Exploring different dimensions of attention for uncertainty detection. In: Lapata, M., Blunsom, P., Koller, A. (eds.) Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2017), Stroudsburg, pp. 22–34. Association for Computational Linguistics (2017)
Qian, Z., Li, P., Zhu, Q.: A two-step approach for event factuality identification. In: Proceedings of 19th International Conference on Asian Language Processing (IALP 2015), pp. 10–16 (2015)
Kim, J.D., Ohta, T., Tateisi, Y., Tsujii, J.: GENIA corpus—a semantically annotated corpus for bio-textmining. Bioinformatics 19(suppl 1), i180–i182 (2003)
Kilicoglu, H., Rosemblat, G., Cairelli, M.J., et al.: A compositional interpretation of biomedical event factuality. In: Proceedings of the 2nd Workshop on Extra-Propositional Aspects of Meaning in Computational Semantics (ExProM 2015), pp. 22–31 (2015)
Pustejovsky, J., Castano, J.M., Ingria, R., et al.: TimeML: robust specification of event and temporal expressions in text. In: Proceedings of the 5th International Workshop on Computational Semantics (IWCS, 2003) (2003)
Linguistic Data Consortium. ACE (Automatic Concept Extraction) Chinese Event Guidelines V5.5.1. [EB/OL], 7 Jan 2005
Cao, Y., Zhu, Q., Li, P.: The construction of Chinese event factuality corpus. J. Chin. Inf. Process. 27(6), 38–44 (2012). (in Chinese)
Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. In: Proceedings of Workshop at ICLR (ICLR 2013) (2013)
Tian, J., Zhao, W.: Word similarity calculating method based on synonym word forest. J. Jilin Univ. 28(06), 602–608 (2010). (in Chinese)
He, T., Li, P., Zhu, Q.: Approach to identify Chinese event factuality. J. Chin. Inf. Process. 44(5), 241–244+256 (2017). (in Chinese)
Neubauer, C.: Shape, position and size invariant visual pattern recognition based on principles of neocognitron and perceptron. [EB/OL] (1992)
Liu, Y., Wei, F., Li, S., et al.: A dependency based neural network for relation classification. Compare Science, pp. 285–290 (2015)
Kim, Y.: Convolutional Neural Networks for Sentence Classification. arXiv preprint arXiv:1408.5882 (2014)
Acknowledgments
This research was supported by National Natural Science Foundation of China (Grants No. 61703293, No. 61672368, No. 61673290). The authors would like to thank the anonymous reviewers for their insightful comments and suggestions.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Sheng, J., Zou, B., Gong, Z., Hong, Y., Zhou, G. (2019). Chinese Event Factuality Detection. In: Tang, J., Kan, MY., Zhao, D., Li, S., Zan, H. (eds) Natural Language Processing and Chinese Computing. NLPCC 2019. Lecture Notes in Computer Science(), vol 11839. Springer, Cham. https://doi.org/10.1007/978-3-030-32236-6_44
Download citation
DOI: https://doi.org/10.1007/978-3-030-32236-6_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32235-9
Online ISBN: 978-3-030-32236-6
eBook Packages: Computer ScienceComputer Science (R0)
