Digital Library

cab1

 
Title:      A QUESTION ANSWERING SYSTEM BASED ON GRAMMATICAL STRUCTURE MATCHING
Author(s):      Ahad Niknia , Leila Sharif Hassanabadi
ISBN:      978-972-8924-97-3
Editors:      Hans Weghorn and Pedro Isaías
Year:      2009
Edition:      V I, 2
Keywords:      Question Answering System, Answer Extraction, Natural Language Processing, POS-Tagging, Information Retrieval
Type:      Full Paper
First Page:      165
Last Page:      172
Language:      English
Cover:      cover          
Full Contents:      click to dowload Download
Paper Abstract:      This paper introduces an Open Domain Question Answering system for wh-questions based on grammatical structure of questions and the corresponding answers. This system also uses IR methods for efficient processing. We introduce our reduced tags set and scoring system for grammatical structures of questions and answers. The system uses POS-taggers because of their simplicities and reliable structures based on PCFG grammars to produce tags for questions and document sentences as our entry sentences. After tags for a given question extracted, the system uses proposed answer table to obtain possible answer's grammatical structure and their values. Then give the results to special search engine, based on new index system that is proposed in this paper, and extracts possible answers to a given question with a score associated to each of them. Then proposes a special formula – based on advanced IR techniques and grammatical analyze - for ranking our candidate sentences. Finally we produce answer's list for a given question to user in decreasing order.
   

Social Media Links

Search

Login