Research on Answer Extraction for Automatic Question Answering System

DOI

10.2991/iccia-19.2019.34How to use a DOI?

Keywords

Automatic Question Answering, Answer Extraction, Pattern Matching, Similarity.

Abstract

The question answering system as a hot issue in the field of NLP study, and answer extraction as the core part of the automatic question answering system, its effect is good or bad is directly related to the performance of question answering system, this paper introduces the technical process of answer extraction module and the use of pattern matching technology, gradually shift from the traditional pattern matching technology to the machine learning method of pattern matching technology, and also calculate the questions and answers in the answer extraction module are several methods of similarity. Since the performance of the automatic question answering system depends on the algorithm used for answer extraction to a large extent, the selection of the algorithm for answer extraction is also crucial, and the accuracy of the answer returned to the user can be improved by improving the algorithm.

Copyright

© 2019, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Tiantian Wu
AU  - Hongzhi Yu
AU  - Fucheng Wan
AU  - Fangtao Yang
PY  - 2019/07
DA  - 2019/07
TI  - Research on Answer Extraction for Automatic Question Answering System
BT  - Proceedings of the 3rd International Conference on Computer Engineering, Information Science & Application Technology (ICCIA 2019)
PB  - Atlantis Press
SP  - 231
EP  - 236
SN  - 2352-538X
UR  - https://doi.org/10.2991/iccia-19.2019.34
DO  - 10.2991/iccia-19.2019.34
ID  - Wu2019/07
ER  -