触发词的识别在事件检测任务中起着至关重要的作用。目前没有越南语触发词标记语料,而中文触发词标记语料较为丰富,根据表达相同观点但语言不同的句子通常有相同或相似的语义成分这一特征,该文提出一种基于中文触发词指导的越南语新闻事件检测方法。首先采用对抗学习的方法将两种语言映射到同一语义空间下,然后将映射后的中文触发词嵌入指导模型识别越南语新闻中的触发词信息,最后进行事件类型的分类。通过在越南语新闻事件检测的实验结果表明,在中文触发词指导下的越南语新闻事件检测取得了较好的效果。
Abstract
The recognition of triggers plays an important role in detecting events.There is no Vietnamese triggers marking corpus at present, but the Chinese triggers marking corpus is relatively rich. Based on the observation that sentences conveying identical idea but in different languages usually have the same or similar semantic components, the paper puts forward a detection method of Vietnamese news event guided by Chinese triggers. Firstly, the two languages are mapped into the same semantic space by adversarial learning. Then the Chinese triggers embeddings are mapped into the guidance model to identify the triggers information in Vietnamese news. Finally, the events types in Vietnamese news are classified. The experimental result shows that the Vietnamese news event detection achieves a better performance on the guidance of Chinese triggers.
关键词
越南语新闻 /
事件检测 /
触发词 /
对抗学习
{{custom_keyword}} /
Key words
vietnamese news /
event detection /
triggers /
adversarial learning
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] JI H, GRISHMAN R. Refining event extraction through cross-document inference[C]//Proceedings of ACL-08: HLT. Columbus,Ohio:ACL, 2008: 254-262.
[2] LI Q, JI H, HUANG L. Joint event extraction via structured prediction with global features [C]//Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics. Sofia,Bulgaria:ACL, 2013:73-82.
[3] TONG M, XU B, WANG S, et al. Improving event detection via open-domain trigger knowledge[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Online:ACL,2020: 5887-5897.
[4] CHEN Z, JI H. Can one language bootstrap the other: A case study on event extraction[C]//Proceedings of the NAACL HLT Workshop on Semi-Supervised Learning for Natural Language Processing, Boulder,Colorado: ACL, 2009: 66-74.
[5] ZHU Z, LI S H, Zhou G D. Bilingual event extraction: A case study on trigger type determination[C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics. Baltimore, Maryland: ACL, 2014: 842-847
[6] HSI A, YANG M, Carbonell J. Leveraging multilingual training for limited resource event extraction[C]//Proceedings of the 26th International Conference on Computational Linguistics: Technical Papers. Osaka,Japan:The COLING Organizing Committee, 2016: 1201-1210.
[7] Ahn D. The stages of event extraction [C]//Proceedings of the Workshop on Annotating and Reasoning About Time and Events. Sydney,Australia: ACL, 2006: 1-8.
[8] LI Q, JI H. Incremental joint extraction of entity mentions and relations[C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics. Baltimore, Maryland: ACL, 2014: 402-412.
[9] CHEN Y B, XU L H, LIU K. Event extraction via dynamic multi-pooling convolutional neural networks[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. Beijing,China: ACL,2015: 167-176.
[10] NGUYEN T H, CHO K, GRISHMAN R. Joint event extraction via recurrent neural networks[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. San Diego,California:NAACL, 2016: 300-309.
[11] NGUYEN T H,GRISHMAN R. Modeling skip-grams for event detection with convolutional neural networks[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing. Austin, Texas: ACL, 2016: 886-891.
[12] CHEN Y B, LIU S L, ZHANG X, et al. Automatically labeled data generation for large scale event extraction[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. Vancouver,Canada:ACL,2017: 409-419.
[13] LIU H L, LIU K, HE H Z. A probabilistic soft logic based approach to exploiting latent and global information in event classification[C]//Proceedings of the 30th AAAI Conference on Artificial Intelgence.Phoenix,Arizna,USA, 2016: 2993-2999.
[14] LIU S L, CHEN Y B, LIU K, et al. Exploiting argument information to improve event detection via supervised attention mechanisms[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics.Vancouver,Canada:ACL, 2017: 1789-1798.
[15] CHEN Y B, YANG H, LIU K, et al. Collective event detection via a hierarchical and bias tagging networks with gated multi-level attention mechanisms[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing. Brussels,Belgium:EMNLP,2018: 1267-1276.
[16] FENG X H, HUANG L F, TANG D Y, et al. A language-independent neural network for event detection[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. Berlin,Germany :ACL, 2016:66-71.
[17] HUANG L F, JI H, MAY J. Cross-lingual multi-level adversarial transfer to enhance low-resource name tagging[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguitics:Human Language Technologies,Volume 1. Minneapolis,Minnesota:NAACL,2019: 735-744.
[18] LI S L, LI Y, ZHOU X P,et al. Event detection without triggers[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguitics:Human Language Technologies. Minneapolis, Minnesota: NAACL, 2019: 735-744.
[19] MIKOLOV T,SUTSKEVER I,CHEN K,et al. Distributed represertations of words and phraqses and their compositiontity[C]//Proceedings of the 26th International Conference on Neural Information Processing Systems, 2013: 3111-2119.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家重点研发计划(2018YFC0830105,2018YFC0830100); 国家自然科学基金(61972186,U21B2027,61761026,61762056);云南高新技术产业发展项目(201606);云南省重大科技专项计划(202002AD080001,202103AA080015);云南省基础研究计划(202001AS070014,2018FB104);云南省科技人才与平台计划(202105AC160018)
{{custom_fund}}
PDF(2192 KB)
