事件同指消解是一个具有挑战性的自然语言处理任务,它在事件抽取、问答系统和阅读理解等任务中发挥着重要作用。现存的事件同指消解语料库的一个问题是标注规模较小,无法训练出高效能的模型。为了解决上述问题,该文提出了一个基于跨语言数据增强的事件同指消解神经网络模型ECR_CDA(Event Coreference Resolution on Cross-lingual Data Augmentation)。该模型通过中英文语料互译来增强语料,并通过共享模型参数的方式实现中英文模型的跨语言学习,从而提高了事件同指消解的性能。在ACE 2005英文语料上的实验结果表明,ECR_CDA优于目前最先进的基准系统。
Abstract
Event coreference resolution is a challenging task with wide application in event extraction, QA system, and reading comprehension. The best use the existing small-scale public corpus, this paper introduces a neural network model ECR_CDA based on cross-lingual data augmentation. This model enhances the corpus through the translation of Chinese and English corpus, and improves the performance of event coreference resolution via the cross-lingual learning of Chinese and English models by sharing the model parameters. The experimental results on ACE 2005 English test set show that ECR_CDA is superior to the most advanced baseline.
关键词
事件同指 /
事件实例短句 /
中英跨语言学习 /
全局优化方法
{{custom_keyword}} /
Key words
event coreference /
single event /
Chinese and English cross-lingual learning /
global optimization method
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Mohammed M Found, Marwa A Atyah. Efficient topic detection system for online arabic news[J]. Computer Applications, 2018: 7-12.
[2] Liang Cheng, Hongkui Gao, Hongbin Wang. A news event extraction method in Chinese and Thai languages based on dependency tree elements combined with rules[J]. Software Guide, 2018.
[3] Swayamdipta, Swabha, Parikh, Ankur P, et al. Multi-mention learning for reading comprehension with neural cascades[C]//Proceedings of the International Conference on Learning Representations, 2018.
[4] Yaosheng Yang, Wenliang Chen, Zhenghua Li,et al. Distantly supervised NER with partial annotation learning and reinforcement learning[C]//Proceedings of the International Conference on Computational Linguistics, 2018: 2159-2169.
[5] Haghighi A, Dan K. Simple coreference resolution with rich syntactic and semantic features[C]//Proceedings of the Meeting of the Empirical Methods in Natural Language Processing, 2009: 1152-1161.
[6] Zhen Chen, Heng Ji. Graph-based event coreference resolution[C]//Proceedings of the Annual Meeting of the Association for Computational Linguistic, 2009: 54-57.
[7] Zhen Chen, Heng Ji. A pairwise event coreference model, feature impact and evaluation for event coreference resolution[C]//Proceedings of the Annual Meeting of the Association for Computational Linguistics, 2009: 17-22.
[8] Zhengzhong Liu, Jun Araki, Eduard Hovy, et al. Supervised within-document event coreference using information propagation[J]. Computer Science, 2014: 4539-4544.
[9] Jing Lu, Vincent Ng. Joint learning for event coreference resolution[C]//Proceedings of the Annual Meeting of the Association for Computational Linguistics, 2017: 90-101.
[10] Zhengzhong Liu, Teruko Mitamura, Eduard Hovy. Graph-based decoding for event sequencing and coreference resolution[C]//Proceedings of the Computational Natural Language Learning, 2018.
[11] Zhu Zhu, Shoushan Li, Guodong Zhou, et al. Bilingual event extraction: a case study on trigger type determination[C]//Proceedings of the Annual Meeting of the Association for Computational Linguistics, 2014: 842-847.
[12] Sebastian Krause, Feiyu Xu, Hans Uszkoreit. Event linking with sentential features from convolutional neural networks[C]//Proceedings of the Computational Natural Language Learning, 2016: 239-249.
[13] Jie Fang, Peifeng Li, Guodong Zhou. Employing multiple decomposable attention networks to resolve event coreference[C]//Proceedings of the International Conference on Natural Language Processing and Chinese Computing, 2018.
[14] 程昊熠,李培峰,朱巧明. 基于注意力机制的事件同指消解方法[J]. 计算机科学, 2019, 9(9): 201-205.
[15] Yin Jou Huang, Jing Lu, Sadao Kurohashi, Vincent Ng. Improving event coreference resolution by learning argument compatibility from unlabeled Data[C]//North American Chapter of the Association for Computational Linguistics, 2019: 785-795.
[16] Gorka Urbizu, Ander Soraluze, Olatz Arregi. Deep cross-lingual coreference resolution for less-resourced languages: the case of Basque[C]//Proceedings of the Computational Models of Reference, Anaphora and Coreference, 2019: 35-41.
[17] Ananya Subburathinam, Di Lu, Heng Ji, et al. Cross-lingual structure transfer for relation and event extraction[C]//Proceedings of the Empirical Methods in Natural Language Processing, 2019: 313-325.
[18] Shen Xu, Peifeng Li, Guodong Zhou, Qiaoming Zhu. Employing text matching network to recognise nuclearity in Chinese discourse[C]//Proceedings of the International Conference on Computational Linguistics, 2018: 525-535.
[19] Marc Vilain, John Burger, John Aberdeen. A model-theoretic coreference scoring scheme[C]//Proceedings of the Conference on Message Understanding, 1995: 45-52.
[20] Amit Bagga, Breck Baldwin. Algorithms for scoring coreference chains[C]//Proceedings of the Language Resources and Evaluation Conference, 1998: 563-566.
[21] Marta Recasen, Eduard Hovy. BLANC: Implementing the rand index for coreference evaluation[J]. Natural Language Engineering, 2011: 485-510.
[22] Xiaoqiang Luo. On coreference resolution performance metrics[C]//Proceedings of the Empirical Methods in Natural Language Processing, 2005: 25-32.
[23] 宦敏, 程昊熠, 李培峰. 基于结构化表示的中文事件同指消解方法[J]. 中文信息学报, 2019, 33(12): 19-27.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(61773276,61472265,61772354);江苏高校优势学科建设工程资助项目
{{custom_fund}}
PDF(1670 KB)
