基于GCN和门机制的汉语框架排歧方法

PDF(3009 KB)

中文信息学报 ›› 2024, Vol. 38 ›› Issue (3) : 33-41.

语言分析与计算模型

基于GCN和门机制的汉语框架排歧方法

游亚男¹,李茹^1,2,苏雪峰^1,3,闫智超¹,孙民帅¹,王超¹

作者信息 +

Chinese Frame Disambiguation Method Based on GCN and Gate Mechanism

YOU Ya'nan¹, LI Ru^1,2, SU Xuefeng^1,3, YAN Zhichao¹, SUN Minshuai¹, WANG Chao¹

Author information +

History +

摘要

汉语框架排歧旨在在候选框架中给句子中的目标词选择一个符合其语义场景的框架。目前研究方法存在隐层向量的计算与目标词无关、忽略了句法结构信息对框架排歧的影响等缺陷。针对上述问题,该文使用GCN对句法结构信息进行建模;引入门机制过滤隐层向量中与目标词无关的噪声信息;并在此基础上,提出一种约束机制来约束模型的学习,改进向量表示。该模型在CFN、FN1.5和FN1.7数据集上优于当前最好模型,证明了该方法的有效性。

Abstract

Chinese frame disambiguation aims to select a proper frame to match the semantic scene of the target word in a specific sentence. This paper proposed a GCN based method for Chinese frame disambiguation to model the syntactic structure in the sentence. A gate mechanism is introduced to filter the noise information irrelevant to the target word in the hidden layer vector. On this basis, a constraint mechanism is proposed to optimize the learning of the model and improve the representation vector . The model outperforms the state-of-the-art models on the CFN, FN1.5 and FN1.7 datasets.

导出引用

游亚男,李茹,苏雪峰,闫智超,孙民帅,王超. 基于GCN和门机制的汉语框架排歧方法. 中文信息学报. 2024, 38(3): 33-41

YOU Ya'nan, LI Ru, SU Xuefeng, YAN Zhichao, SUN Minshuai, WANG Chao. Chinese Frame Disambiguation Method Based on GCN and Gate Mechanism. Journal of Chinese Information Processing. 2024, 38(3): 33-41

参考文献

[1] YOU L, LIU K. Building Chinese framenet database [J].Natural Language Processing and Knowledge Engineering, 2005: 301-306.
[2] FILLMORE C J. Frame semantics and the nature of language[C]//Proceedings of the Annals of the New York Academy of Sciences: Conference on the Origin and Development of Language and Speech, 1976, 280: 20-32.
[3] BAKER C F, FILLMORE C J, LOWE J B. The Berkeley framenet project[C]//Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics, 1998: 86-90.
[4] 李茹. 汉语句子框架语义结构分析技术研究[D]. 太原: 山西大学硕士学位论文,2012.
[5] 石佼, 李茹, 王智强. 汉语核心框架语义分析[J]. 中文信息学报, 2014, 28(6): 48-55.
[6] KENTON J D M W C, TOUTANOVA L K. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding[C]//Proceedings of NAACL-HLT. 2019: 4171-4186.
[7] CHE W, LI Z, LIU T. LTP: A Chinese language technology platform [C]//Proceedings of the COLING, Demonstrations, Beijing, China,2010:13-16.
[8] BAKER C, ELLSWORTH M, ERK K. SemEval-2007 Task 19: Frame semantic structure extraction [C]//Proceedings of the 4th International Workshop on Semantic Evaluations, 2007: 99-104.
[9] 李济洪, 高亚慧, 王瑞波,等. 汉语框架自动识别中的歧义消解[J].中文信息学报, 2011, 25(03): 38-44.
[10] 李国臣, 张立凡, 李茹,等. 基于词元语义特征的汉语框架排歧研究[J]. 中文信息学报, 2013, 27(4): 44-52.
[11] HERMANN K M, DAS D, WESTON J, et al. Semantic frame identification with distributed word representations[C]//Proceedings of the Meeting of the Association for Computational Linguistics. Baltimore, USA, 2014: 1448-1458.
[12] 赵红燕, 李茹, 张晟, 等. 基于 DNN 的汉语框架识别研究[J]. 中文信息学报, 2016, 30(6): 75-83.
[13] 张力文, 王瑞波, 李茹,等. 基于词分布式表征的汉语框架排歧模型[J]. 中文信息学报, 2017, 31(06): 50-57.
[14] BOTSCHEN T, MOUSSELLY SERGIEH H, GUREVYCH I. Prediction of frame-to-frame relations in the FrameNet hierarchy with frame embeddings[C]//Proceedings of the 2nd Workshop on Representation Learning for NLP, 2017: 146-156.
[15] 侯运瑶, 曹学飞, 崔军,等. 基于框架表示学习的汉语框架排歧[J]. 计算机应用研究, 2020, 37(12): 5-17.
[16] 郭哲铭. 基于注意力机制的框架识别技术研究[D]. 太原:山西大学硕士学位论文, 2021.
[17] SU X, LI R, LI X, et al. A knowledge-guided framework for frame identification[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2021.
[18] LI R, LIU H, LI S. Chinese frame identification using T-CRF model [C]//Proceedings of International Conference on Computional Linguistics,Beijing, 2010: 674-682.
[19] 王智强, 李茹, 阴志洲,等. 基于依存特征的汉语框架语义角色自动标注[J]. 中文信息学报, 2013, 27(2): 34-40.
[20] KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[C]//Proceedings of the International Conference on Learning Representations, 2016.
[21] ZHANG Y, QI P, MANNING C D. Graph convolution over pruned dependency trees improves relation extraction[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 2018.
[22] DU Y, HOLLA N, ZHEN X, et al. Meta-learning with variational semantic memory for word sense disambiguation[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. 2021: 5254-5268.
[23] HOLLA N, MISHRA P, YANNAKOUDAKIS H, et al. Learning to learn to disambiguate: Meta-learning for few-shot word sense disambiguation[C]//Proceedings of the Association for Computational Linguistics: EMNLP, 2020: 4517-4533.
[24] CHEN H, XIA M, CHEN D. Non-parametric few-shot learning for word sense disambiguation[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics, 2021: 1774-1781.
[25] KUMAR S, JAT S, SAXENA K, et al. Zero-shot word sense disambiguation using sense definition embeddings[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019: 5670-5681.
[26] LI Q, HAN Z, WU X M. Deeper insights into graph convolutional networks for semi-supervised learning[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2018.

基金

国家自然科学基金(61936012);中新语言智能国际联合实验室(110037901001);山西工程科技职业大学校科研基金计划项目(KJ202203);山西省“四个一批”科技兴医创新计划项目(2022XM01);面向战略性新兴产业的企业创新能力画像自动生成关键技术研究及应用(202102020101008)

PDF(3009 KB)

391

Accesses

Citation

Detail

段落导航

摘要
Abstract
关键词
Key words
引用本文
参考文献
基金

选择文件类型/文献管理软件名称

选择包含的内容

摘要

Abstract

关键词

Key words

引用本文

{{custom_sec.title}}

{{custom_sec.title}}

参考文献

{{custom_fnGroup.title_cn}}

脚注

基金

Published
2024-04-26
Issue Date
2024-04-29