Abstract
Pronoun-drop is a common phenomenon in Chinese, zero pronoun resolution aims to recover the pronoun and resolve the anaphora antecedent of the pronoun, which is important for NLP tasks such as machine translation, information extraction, etc. Most of the existing research methods predefined zero pronoun sets. Zero pronoun recovery is carried out through multi-classification, and then the coreference chains between each pronoun and the candidate antecedent are predicted in turn. However, most of the previous methods only focus on the relationship between pronouns and arguments, ignoring the deep semantic relationship between predicates and arguments as the core semantic component. In addition, the model takes the parse tree (gold tree) as a priori knowledge, which is costly in practical applications. In this paper, we propose a Machine Reading Comprehension model combined with Semantic Dependency (MRC-SD), which takes advantage of the feature that semantic dependencies can directly access deep semantic information across the surface syntactic structure of a sentence to capture the semantic relations between predicates and arguments, and enhance such semantic relations in the form of questions and answers through machine reading comprehension, to extract co-reference chains more accurately. In addition, we propose a method of combining semantic dependency with the language model to realize zero pronoun recovery from the deep semantic level. Experimental results on our self-constructed public opinion dataset (FS-PO) show that the MRC-SD model significantly outperforms the state-of-the-art zero-pronoun resolution model.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Aloraini A, Poesio M (2020) Cross-lingual zero pronoun resolution. In: Proceedings of The 12th language resources and evaluation conference, pp 90–98
Bi M, Zhang Q, Zuo M, Xu Z, Jin Q (2020) Bi-directional lstm model with symptoms-frequency position attention for question answering system in medical domain. Neural Process Lett 51(2):1185–1199
Bi M, Zhang Q, Zuo M, Xu Z, Jin Q (2021) Bi-directional long short-term memory model with semantic positional attention for the question answering system. Trans Asian Low-Resour Lang Inf Process 20(5):1–13
Chen C, Ng V (2013) Chinese zero pronoun resolution: Some recent advances. In: Proceedings of the 2013 conference on empirical methods in natural language processing, pp 1360–1365
Chen C, Ng V (2015) Chinese zero pronoun resolution: A joint unsupervised discourse-aware model rivaling state-of-the-art resolvers. In: Proceedings of the 53rd annual meeting of the association for computational linguistics and the 7th international joint conference on natural language processing (volume 2: short papers), pp 320–326
Chen C, Ng V (2016) Chinese zero pronoun resolution with deep neural networks. In: Proceedings of the 54th annual meeting of the association for computational linguistics (volume 1: long papers), pp 778–788
Chen HY, Zhou E, Choi JD (2017) Robust coreference resolution and entity linking on dialogues: character identification on tv show transcripts. In: Proceedings of the 21st conference on computational natural language learning (CoNLL 2017), pp 216–225
Chen S, Gu B, Qu J, Li Z, Liu A, Zhao L, Chen Z (2021) Tackling zero pronoun resolution and non-zero coreference resolution jointly. In: Proceedings of the 25th conference on computational natural language learning, pp 518–527
Choi E, He H, Iyyer M, Yatskar M, Yih Wt, Choi Y, Liang P, Zettlemoyer L (2018) Quac: Question answering in context. arXiv preprint arXiv:1808.07036
Cui Y, Che W, Liu T, Qin B, Yang Z (2021) Pre-training with whole word masking for Chinese Bert. IEEE/ACM Trans Audio Speech Lang Process 29:3504–3514
Hemmatian F, Sohrabi MK (2019) A survey on classification techniques for opinion mining and sentiment analysis. Artif Intell Rev 52(3):1495–1545
Liu T, Cui Y, Yin Q, Zhang W, Wang S, Hu G (2016) Generating and exploiting large-scale pseudo training data for zero pronoun resolution. arXiv preprint arXiv:1606.01603
Phan MH, Ogunbona PO (2020) Modelling context and syntactical features for aspect-based sentiment analysis. In: Proceedings of the 58th annual meeting of the association for computational linguistics, pp 3211–3220
Rana TA, Cheah YN (2016) Aspect extraction in sentiment analysis: comparative analysis and survey. Artif Intell Rev 46(4):459–483
Reddy S, Chen D, Manning CD (2019) Coqa: a conversational question answering challenge. Trans Assoc Comput Ling 7:249–266
Rolih G (2018) Applying coreference resolution for usage in dialog systems
Song L, Xu K, Zhang Y, Chen J, Yu D (2020) Zpr2: Joint zero pronoun recovery and resolution using multi-task learning and Bert. In: Proceedings of the 58th annual meeting of the association for computational linguistics, pp 5429–5434
Sun K, Yu D, Chen J, Yu D, Choi Y, Cardie C (2019) Dream: a challenge data set and models for dialogue-based reading comprehension. Trans Assoc Comput Ling 7:217–231
Takeno S, Nagata M, Yamamoto K (2016) Integrating empty category detection into preordering machine translation. In: Proceedings of the 3rd workshop on Asian translation (WAT2016), pp 157–165
Wang L, Tu Z, Zhang X, Li H, Way A, Liu Q (2016) A novel approach to dropped pronoun translation. arXiv preprint arXiv:1604.06285
Xiang B, Luo X, Zhou B (2013) Enlisting the ghost: modeling empty categories for machine translation. In: Proceedings of the 51st annual meeting of the association for computational linguistics (volume 1: long papers), pp 822–831
Xu H, Chen Y, Sun J, Cao X, Xie R (2020a) Iterative strategy for named entity recognition with imperfect annotations. In: CCF international conference on natural language processing and Chinese computing, Springer, pp 512–523
Xu L, Hu H, Zhang X, Li L, Cao C, Li Y, Xu Y, Sun K, Yu D, Yu C, Tian Y, Dong Q, Liu W, Shi B, Cui Y, Li J, Zeng J, Wang R, Xie W, Li Y, Patterson Y, Tian Z, Zhang Y, Zhou H, Liu S, Zhao Z, Zhao Q, Yue C, Zhang X, Yang Z, Richardson K, Lan Z (2020b) CLUE: a Chinese language understanding evaluation benchmark. In: Proceedings of the 28th international conference on computational linguistics, International Committee on Computational Linguistics, Barcelona, Spain (Online), pp 4762–4772, https://doi.org/10.18653/v1/2020.coling-main.419,https://aclanthology.org/2020.coling-main.419
Yang Y, Liu Y, Xue N (2015) Recovering dropped pronouns from Chinese text messages. In: Proceedings of the 53rd annual meeting of the association for computational linguistics and the 7th international joint conference on natural language processing (volume 2: short papers), pp 309–313
Yang W, Qiao R, Qin H, Sun A, Tan L, Xiong K, Li M (2019) End-to-end neural context reconstruction in Chinese dialogue. In: Proceedings of the first workshop on NLP for conversational AI, pp 68–76
Yang J, Xu K, Xu J, Li S, Gao S, Guo J, Wen JR, Xue N (2020) Transformer-gcrf: recovering Chinese dropped pronouns with general conditional random fields. arXiv preprint arXiv:2010.03224
Yin Q, Zhang Y, Zhang W, Liu T, Wang WY (2018a) Deep reinforcement learning for Chinese zero pronoun resolution. arXiv preprint arXiv:1806.03711
Yin Q, Zhang Y, Zhang W, Liu T, Wang WY (2018b) Zero pronoun resolution with attention-based neural network. In: Proceedings of the 27th international conference on computational linguistics, pp 13–23
Zhao S, Ng HT (2007) Identification and resolution of Chinese zero pronouns: a machine learning approach. In: Proceedings of the 2007 joint conference on empirical methods in natural language processing and computational natural language learning (EMNLP-CoNLL), pp 541–550
Acknowledgements
This study is supported by National Key Technology R &D Program of China (No. 2021YFD2100605), Beijing Natural Science Foundation (No. 4202014), Humanity and Social Science Youth Foundation of Ministry of Education of China (No. 20YJCZH229) and Beijing Science and Technology Planning Project (No. Z191100008619007)
Author information
Authors and Affiliations
Corresponding authors
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Bi, M., Liu, X., Zhang, Q. et al. Machine reading comprehension combined with semantic dependency for Chinese zero pronoun resolution. Artif Intell Rev 56, 7597–7612 (2023). https://doi.org/10.1007/s10462-022-10364-5
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10462-022-10364-5