arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2103.05135cs.CL
收藏

基于一种新的句法N-gram变体的文档语义拓扑比较方法

A Topological Approach to Compare Document Semantics Based on a New Variant of Syntactic N-grams

Biocomplexity Institute University of Virginia(弗吉尼亚大学生物复杂性研究所)

Fanchao Meng

摘要:

本文提供了一个新的角度来思考和利用句法n-gram(sn-gram)。Sn-gram是一种非线性n-gram,在许多NLP任务中发挥着重要作用。因此,引入sn-gram来比较文档语义是一个有吸引力的应用,很少有研究报告在这方面取得了进展。然而,当我们继续在这个应用程序中,我们发现三个主要的问题:缺乏意义,是敏感的词序和未能捕捉间接的句法关系。为了解决这些问题,我们提出了一个新的变体的sn-元命名为广义短语(GP)。然后,基于GP,我们提出了一种拓扑方法,命名为DSCoH,计算文档语义相似度。DSCoH已经在文档语义比较和文档聚类任务上进行了广泛的测试。实验结果表明,DSCoH可以优于最先进的嵌入式方法。

英文摘要:

This paper delivers a new perspective of thinking and utilizing syntactic n-grams (sn-grams). Sn-grams are a type of non-linear n-grams which have been playing a critical role in many NLP tasks. Introducing sn-grams to comparing document semantics thus is an appealing application, and few studies have reported progress at this. However, when proceeding on this application, we found three major issues of sn-grams: lack of significance, being sensitive to word orders and failing on capture indirect syntactic relations. To address these issues, we propose a new variant of sn-grams named generalized phrases (GPs). Then based on GPs we propose a topological approach, named DSCoH, to compute document semantic similarities. DSCoH has been extensively tested on the document semantics comparison and the document clustering tasks. The experimental results show that DSCoH can outperform state-of-the-art embedding-based 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。

↑