Near-synonym substitution using a discriminative vector space model

NCUIR > College of Electrical Engineering & Computer Science > Department of Electrical Engineering > journal & Dissertation > Item 987654321/107865

Please use this identifier to cite or link to this item: https://ir.lib.ncu.edu.tw/handle/987654321/107865

Title:	Near-synonym substitution using a discriminative vector space model
Authors:	李龍豪;Yu, Liang-Chih;Lee, Lung-Hao;Yeh, Jui-Feng;Shih, Hsiu-Min;Lai, Yu-Ling
Contributors:	資訊電機學院電機工程學系
Keywords:	Algorithms;Classification;Discriminative training;Knowledge base;Learning;Lexical substitution;Natural language processing;Near-synonym learning;On-line systems;Tasks;Training;Vector space model;Vector spaces
Date:	2016-08-15
Issue Date:	2026-04-23 14:27:36 (UTC+8)
Publisher:	Elsevier;Elsevier B.V
Abstract:	摘要： Near-synonyms are fundamental and useful knowledge resources for computer-assisted language learning (CALL) applications. For example, in online language learning systems, learners may have a need to express a similar meaning using different words. However, it is usually difficult to choose suitable near-synonyms to fit a given context because the differences of near-synonyms are not easily grasped in practical use, especially for second language (L2) learners. Accordingly, it is worth developing algorithms to verify whether near-synonyms match given contexts. Such algorithms could be used in applications to assist L2 learners in discovering the collocational differences between near-synonyms. We propose a discriminative vector space model for the near-synonym substitution task, and consider this task as a classification task. There are two components: a vector space model and discriminative training. The vector space model is used as a baseline classifier to classify test examples into one of the near-synonyms in a given near-synonym set. A discriminative training technique is then employed to improve the vector space model by distinguishing positive and negative features for each near-synonym. Experimental results show that the DT-VSM achieves higher accuracy than both pointwise mutual information and n-gram-based methods that have been used in previous studies. 出版者： Elsevier B.V 出版日期： 2016-08-15 出處： Knowledge-based systems, 2016-08, Vol.106, p.74-84 資源來源： Access articles in the ScienceDirect collection 版權： 2016 Elsevier B.V. 識別號： ISSN: 0950-7051 識別號： EISSN: 1872-7409 識別號： DOI: 10.1016/j.knosys.2016.05.025
Appears in Collections:	[Department of Electrical Engineering] journal & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	11	View/Open

社群 sharing

Loading...