文章基本信息

标题：Answer Extraction and Passage Retrieval for Question Answering Systems
本地全文：下载
作者：Waheeb Ahmed ; Dr. Babu Anto P
期刊名称：International Journal of Advanced Research in Computer Engineering & Technology (IJARCET)
印刷版ISSN：2278-1323
出版年度：2016
卷号：5
期号：12
页码：2703-2706
出版社：Shri Pannalal Research Institute of Technolgy
摘要：Question Answering systems (QASs) do the task ofretrieving text portions from a collection of documents thatcontain the answer to the user’s questions. These QASs use avariety of linguistic tools that be able to deal with smallfragments of text. Therefore, to retrieve the documents whichcontains the answer from a large document collections, QASsemploy Information Retrieval (IR) techniques to minimize thenumber of documents collections to a treatable amount ofrelevant text. In this paper, we propose a model for passageretrieval model that do this task with a better performance forthe purpose of Arabic QASs. We first segment each the top fiveranked documents returned by the IR module into passages.Then, we compute the similarity score between the user’squestion terms and each passage. The top five passages (withhigh similarity score) are retrieved are retrieved. Finally,Answer Extraction techniques are applied to extract the finalanswer. Our method achieved an average for precision of87.25%, Recall of 86.2% and F1-measure of 87%.
关键词：Answer Extraction ;Information Retrieval;Passage Retrieval; Question Answering Systems.