文章基本信息

标题：From Lexical to Semantic Features in Paraphrase Identification
本地全文：下载
作者：Pedro Fialho ; Luísa Coheur ; Paulo Quaresma 等
期刊名称：OASIcs : OpenAccess Series in Informatics
电子版ISSN：2190-6807
出版年度：2019
卷号：74
页码：1-11
DOI：10.4230/OASIcs.SLATE.2019.9
出版社：Schloss Dagstuhl -- Leibniz-Zentrum fuer Informatik
摘要：The task of paraphrase identification has been applied to diverse scenarios in Natural Language Processing, such as Machine Translation, summarization, or plagiarism detection. In this paper we present a comparative study on the performance of lexical, syntactic and semantic features in the task of paraphrase identification in the Microsoft Research Paraphrase Corpus. In our experiments, semantic features do not represent a gain in results, and syntactic features lead to the best results, but only if combined with lexical features.
关键词：paraphrase identification; lexical features; syntactic features; semantic features