arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.01636cs.CLcs.LG
收藏

使用分布感知词嵌入的命名实体识别性能实证研究

Empirical Study of Named Entity Recognition Performance Using Distribution-aware Word Embedding

University of Illinois(伊利诺伊大学)

Xin Chen, Qi Zhao, Xinyang Liu

AI总结:

本文针对NER在陌生实体类型与文档下的识别难题,提出分布感知词嵌入并通过三种方式融入NER框架,验证了词语特异度信息可提升识别性能。

摘要:

随着深度学习技术的快速发展,命名实体识别(NER)在信息抽取任务中变得越来越重要。NER任务面临的最大困难是,即使在命名实体(NE)类型和文档都不熟悉的情况下,也要保持可检测性。我们意识到特异度信息可能包含词语的潜在含义,并能为词嵌入生成语义相关特征,因此开发了一种分布感知词嵌入,并在NER框架中实现了三种不同方法以利用分布信息。结果表明,如果将词语特异度纳入现有NER方法,NER的性能将会得到提升。

英文摘要:

With the fast development of Deep Learning techniques, Named Entity Recognition (NER) is becoming more and more important in the information extraction task. The greatest difficulty that the NER task faces is to keep the detectability even when types of NE and documents are unfamiliar. Realizing that the specificity information may contain potential meanings of a word and generate semantic-related features for word embedding, we develop a distribution-aware word embedding and implement three different methods to make use of the distribution information in a NER framework. And the result shows that the performance of NER will be improved if the word specificity is incorporated into existing NER methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑