Abstract
Ellipsis is a cross-linguistic phenomenon which can be commonly seen in Chinese. Although eliding some of the elements in the sentence that could be understood from the context makes no difference for human beings, it is a great challenge for machine in the procedure of natural language understanding. In order to promote ellipsis-related researches in Chinese language, we propose an application-oriented definition of ellipsis specifically for researches in the realm of Chinese natural language processing. At the same time, we build and release a multi-domain dataset for sentence-level Chinese ellipsis resolution following the new definition we propose. In addition, we define a new task: sentence-level Chinese ellipsis resolution, and model it with two subprocedures: 1) Elliptic position detection; 2) Ellipsis resolution. We propose several baseline methods based on pre-trained language models, as they have obtained state-of-the-art results on related tasks. Besides, it is also worth noticing that, to our knowledge, this is the first study that apply the extractive method for question answering to Chinese ellipsis resolution. The results of the experiments show that it is possible for machine to understand ellipsis within our new definition.
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
Similar content being viewed by others
References
Ren, X., et al.: Building an ellipsis-aware chinese dependency treebank for web text. In: Proceedings of the 12th International Conference on Language Resources and Evaluation (2018)
Liu, Y., et al.: Ellipsis in Chinese AMR corpus.In: Proceedings of the First International Workshop on Designing Meaning Representations, pp. 92–99 (2019)
Yuru, J., Yuyao, Z., Teng, M., et al.: A survey of Chinese Zero anaphora resolution. J. Chin. Inf. Process. 34(3), 1–12 (2020)
Wang, S.: Study of ellipsis. studies of the Chinese Language (6), 409–415 (1985)
Liu, W., et al.: Lexicon enhanced Chinese sequence labeling using BERT adapter. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (vol. 1: Long Papers) (2021)
Yang, H.: BERT Meets Chinese Word Segmentation. arXiv preprint arXiv: 1909.09292 (2019)
Merchant J.: Three types of ellipsis. Context-Depend. Perspect. Relat. 6, 141–192 (2010)
McShane, M.J.: A Theory of Ellipsis. Oxford University Press on Demand (2005)
Aralikatte, R., Lamm, M., Hardt, D., et al.: Ellipsis resolution as question answering: An evaluation. arXiv preprint arXiv:1908.11141 (2019)
Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: Squad: 100,000+ questions for machine comprehension of text. arXiv preprint arXiv:1606.05250 (2016)
Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (2020)
Shao, Y., et al.: CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation. arXiv preprint arXiv:2109.05729 (2021)
Lin, C.-Y.: Rouge: A package for automatic evaluation of summaries. Text summarization branches out. In: Text summarization branches out, pp. 74–81 (2004)
Chao, Y.R.: A Grammar of spoken Chinese. ERIC (1965)
Zhou,K.G., et al.: Corpus construction for Chinese zero anaphora from discourse perspective. J. Softw. 32(12), 3782–3801 (2021)
Duan, D.: The baseline/elaboration organization for the constructional meaning of Chinese Ellipsis Structures. Modern Chin. 464–475 (2022)
Shen, S.: Chinese zero-pronoun resolution based on pretrained language model. Inf. Commun. 41–43 (2020)
Chen, P.: Discourse Analysis of Chinese zero-form anaphora. Stud. Chin. Lang. 5(3), 363–378 (1987)
Hou, M., Sun, J.J., et al.: Zero anaphora in Chinese and how to process it in Chinese-English MT. J. Chin. Inf. Process. 14–20 (2005)
Zheng.: A study on the nature and norm of elliptical sentences. Appl. Linguist. (1998)
Acknowledgements
This research project is supported by the National Natural Science Foundation of China (61872402), the Humanities and Social Science Project of the Ministry of Education (17YJAZH068), Science Foundation of Beijing Language and Culture University (supported by “the Fundamental Research Funds for the Central Universities”) (22YJ080002, 18ZDJ03), the Fundamental Research Funds for the Central Universities, and the Research Funds of Beijing Language and Culture University (22YCX158).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Qi, J., Shao, Y., Li, W., Shen, Z. (2022). MCER: A Multi-domain Dataset for Sentence-Level Chinese Ellipsis Resolution. In: Lu, W., Huang, S., Hong, Y., Zhou, X. (eds) Natural Language Processing and Chinese Computing. NLPCC 2022. Lecture Notes in Computer Science(), vol 13551. Springer, Cham. https://doi.org/10.1007/978-3-031-17120-8_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-17120-8_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-17119-2
Online ISBN: 978-3-031-17120-8
eBook Packages: Computer ScienceComputer Science (R0)
