文章基本信息

标题：Dependency vs. Constituent Based Syntactic N-Grams in Text Similarity Measures for Paraphrase Recognition
本地全文：下载
作者：Hiram Calvo ; Andrea Segura-Olivares ; Alejandro García 等
期刊名称：Computación y Sistemas
印刷版ISSN：1405-5546
出版年度：2014
卷号：18
期号：3
页码：517-554
语种：English
出版社：Instituto Politécnico Nacional
其他摘要：Paraphrase recognition consists in detecting if an expression restated as another expression contains the same information. Traditionally, for solving this prob- lem, several lexical, syntactic and semantic based tech- niques are used. For measuring word overlapping, most of the works use n-grams; however syntactic n-grams have been scantily explored. We propose using syntac- tic dependency and constituent n-grams combined with common NLP techniques such as stemming, synonym detection, similarity measures , and linear combination and a similarity matrix built in turn from syntactic n- grams. We measure and compare the performance of our system by using the Microsoft Research Paraphrase Corpus. An in-depth research is presented in order to present the strengths and weaknesses of each ap- proach, as well as a common error analysis section. Our main motivation was to determine which syntactic approach had a better performance for this task: syn- tactic dependency n-grams, or syntactic constituent n- grams. We compare too both approaches with traditional n-grams and state-of-the-art systems.
关键词：Paraphrase recognition; Microsoft Research paraphrase corpus; similarity measures; syntactic n- grams; constituent analysis; dependency analysis