《计算机应用研究》|Application Research of Computers

基于框架表示学习的汉语框架排歧

Chinese frame disambiguation based on frame representation learning

免费全文下载 (已被下载 次)  
获取PDF全文
作者 侯运瑶,曹学飞,崔军,王瑞波,李济洪,李茹
机构 1.山西大学 a.计算机与信息技术学院;b.软件学院;c.现代教育技术学院,太原 030006;2.山西大学计算智能与中文信息处理教育部重点实验室,太原 030006;3.山西省大数据挖掘与智能技术协同创新中心,太原 030006
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2020)12-024-3640-05
DOI 10.19734/j.issn.1001-3695.2019.09.0535
摘要 为了改善框架排歧模型的性能,区别于传统分类算法人工提取特征的做法,直接从语料中的例句出发,使用神经网络模型给出了一种框架表示学习的算法,并将学习到的框架表示向量用于框架排歧任务,显著提升了框架排歧的性能。该算法充分利用CFN中例句库、词元库,基于hinge-loss的神经网络,学习到能最大区别正确框架与错误框架的框架表示向量。此外,还使用WSABIE算法学习到目标词及其上下文的表示向量,排歧时以上下文表示向量与框架表示向量做余弦夹角来判决。在CFN中88个有歧义的词元上进行3组2折交叉验证(3×2 BCV)实验,框架排歧精度最好达到72.52%,<i>t</i>-检验结果表明该方法性能显著高于其他框架排歧方法。
关键词 框架排歧; 框架表示; 表示学习; 汉语框架语义知识库
基金项目 国家自然科学基金青年基金项目(61806115)
国家自然科学基金项目(61772324)
本文URL http://www.arocmag.com/article/01-2020-12-024.html
英文标题 Chinese frame disambiguation based on frame representation learning
作者英文名 Hou Yunyao, Cao Xuefei, Cui Jun, Wang Ruibo, Li Jihong, Li Ru
机构英文名 1.a.School of Computer & Information Technology,b.School of software,c.School of Modern Educational Technology,Shanxi University,Taiyuan 030006,China;2.Key Laboratory of Computer Intelligence & Chinese Information Processing of Ministry of Education,Shanxi University,Taiyuan 030006,China;3.Collaborative Innovation Center of Big Data Mining & Intelligent Technology in Shanxi,Taiyuan 030006,China
英文摘要 In order to improve the performance of frame disambiguation model, this paper used a neural network model to learn frame representation based on sentences in corpus different from the traditional classification algorithm extracting features manually, and employed the learned frame representation on the frame disambiguation task, which significantly improved the performance of the task. Making full use of the CFN example sentence database and being based on the hinge-loss neural network, the algorithm learnt the frame representation that could distinguish the correct frame from the error frame in the largest degree. This paper also used the WSABIE algorithm to learn the representation vector of the context of the target word, and finally used the cosine distance between the context representation vector and the frame representation vector to make a decision for the task. Experiment performed three sets of two-fold cross-validation(3×2 BCV) on 88 ambiguous words in CFN, and the best accuracy of frame disambiguation reach to 72.52%. The <i>t</i>-test results show that the performance of the proposed method is significantly higher than other frame disambiguation methods.
英文关键词 frame disambiguation; frame representation; representation learning; Chinese FrameNet(CFN)
参考文献 查看稿件参考文献
 
收稿日期 2019/9/11
修回日期 2019/11/9
页码 3640-3644
中图分类号 TP391
文献标志码 A