框架语义角色标注(Frame Semantic Role Labeling, FSRL)是基于FrameNet标注体系的语义分析任务。语义角色标注通常对句法有很强的依赖性,目前的语义角色标注模型大多基于双向长短时记忆网络Bi-LSTM,虽然可以获取句子中的长距离依赖信息,但无法很好地获取句子中的句法信息。因此,引入Self-Attention机制来捕获句子中每个词的句法信息。实验结果表明,该模型在CFN(Chinese FrameNet,汉语框架网)数据集上的F1值得到了提升,证明了融入self-attention机制可以改进汉语框架语义角色标注模型的性能。
Abstract
Frame semantic role labeling is a semantic analysis task based on theFrameNet.Semantic role labeling usually has a strong dependence on syntax. Most of the current semantic role labeling models are based on Bi-LSTM, which can obtain the long-distance dependency information in sentences, but cannot obtain the syntactic information in sentences well.In this paper,we iimental results show that the F1 of the model on the CFN (Chinese FrameNet) dataset has been improved, which proves that the self-attention mechanism can improve the performance of the Chinese frame semantic role labeling model.
关键词
语义角色标注 /
自注意力机制 /
双向长短时记忆网络 /
汉语框架网
{{custom_keyword}} /
Key words
semantic role labeling /
Self-Attention /
Bi-LSTM /
Chinese FramNet
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Surdeanu S,Williams J, Aarseth P. Using predicate-argument structures for information extraction[C]//Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics, 2003:8-15.
[2] Yih W T,Richardson M,Meek C,et al. The value of semantic parse labeling for knowledge base question answering[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics,2016:201-206.
[3] 张苗苗,张玉洁,刘明童,等.基于Gate机制Bi-LSTM-CRF的汉语语义角色标注[J].计算机与现代化, 2018,(4):1-6.
[4] Zhou J, Xu W. End-to-end learning of semantic role labeling using recurrent 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, 2015:1127-1137.
[5] He L H,Lee K,Lewis M,et al.Deep semantic role labeling: what works and whats next[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics,2017: 473-483.
[6] Marcheggiani D,Frolov A,Titov I. A simple and accurate syntax-agnostic neural model for dependency-based semantic role[C]//Proceedings of the 21st Conference on Computational Natural Language Learning, 2017:411-420.
[7] Punyakanok V,Roth D,Yih W T.The importance of syntactic parsing and inferencein semantic role labeling[J].Computational Linguistics,2008,34(2):257-287.
[8] Marcheggiani D, Titov I. Encoding sentences with graph convolutional networks for semantic role labeling[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing,2017:1506-1515.
[9] Gildea D, Jurafsky D. Automatic labeling of semantic roles[J].Computational Linguistics, 2002,28(3):245-288.
[10] Xue N. Labeling Chinese predicates with semantic roles[J].Computational Linguistics,2008,34(2):225-255.
[11] 李济洪,王瑞波,王蔚林,等.汉语框架语义角色的自动标注[J].软件学报,2010,21(4):597-611.
[12] 王蔚林.基于最大熵模型的汉语框架语义角色自动标注[D].太原: 山西大学硕士学位论文,2010.
[13] 屠寒非,李茹,王智强,等.一种基于主动学习的框架元素标注[J].中文信息学报,2016,30(4):44-55.
[14] Ronan C, Jason W. A unified architecture for natural language processing: Deep neural networks with multitask learning[C]//Proceedings of the 25th International Conference, 2008:249-256.
[15] 王臻,常宝宝,穗志方.基于分层输出神经网络的汉语语义角色标注[J].中文信息学报,2014,28(6):51-61.
[16] Wang Z,Jiang T S,Chang B B,et al.Chinese semantic role labeling with bidirectional recurrent neural networks[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing,2015:1626-1631.
[17] 党帅兵.基于词分布表征的汉语框架语义角色识别研究[D].太原: 山西大学硕士学位论文,2015.
[18] 王瑞波,李济洪,李国臣,等.基于Dropout正则化的汉语框架语义角色识别[J].中文信息学报,2017,31(1):147-154.
[19] Tan Z X,Wang M X,Xie J,et al.Deep semantic role labeling with self-attention[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence,2018:4929-4936.
[20] Ouchi H, Shindo H, Matsumoto Y. A span selection model for semantic role labeling[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing,2018:1630-1642.
[21] Roth M,Lapata M.Neural semantic role labeling with dependency path embeddings[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, 2016,1:1192-1202.
[22] Qian F,Sha L,Chang B B,et al.Syntax aware LSTM model for semantic role labeling[C]//Proceedings of the 2nd Workshop on Structured Prediction for Natural Language Processing, 2017: 27-32.
[23] He L H,Kenton L,Omer L,et al.Jointly predicting predicates and arguments in neural semantic role labeling[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics,2018:364-369.
[24] Zhang Y,Wang R,Si L.Syntax-enhanced self-attention-based semantic role labeling[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing,2019: 616-626.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(61772324,61936012)
{{custom_fund}}
PDF(4377 KB)
