IEICE TRANSACTIONS on Information
How to Combine Translation Probabilities and Question Expansion for Question Classification in cQA Services
Summary :
This paper claims to use a new question expansion method for question classification in cQA services. The input questions consist of only a question whereas training data do a pair of question and answer. Thus they cannot provide enough information for good classification in many cases. Since the answer is strongly associated with the input questions, we try to create a pseudo answer to expand each input question. Translation probabilities between questions and answers and a pseudo relevant feedback technique are used to generate the pseudo answer. As a result, we obtain the significant improved performances when two approaches are effectively combined.
- Publication
- IEICE TRANSACTIONS on Information Vol.E99-D No.4 pp.1019-1022
- Publication Date
- 2016/04/01
- Publicized
- 2016/01/14
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2015DAL0005
- Type of Manuscript
- Special Section LETTER (Special Section on Data Engineering and Information Management)
- Category
Authors
Kyoungman BAE
Dong-A University
Youngjoong KO
Dong-A University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Kyoungman BAE, Youngjoong KO, "How to Combine Translation Probabilities and Question Expansion for Question Classification in cQA Services" in IEICE TRANSACTIONS on Information,
vol. E99-D, no. 4, pp. 1019-1022, April 2016, doi: 10.1587/transinf.2015DAL0005.
Abstract: This paper claims to use a new question expansion method for question classification in cQA services. The input questions consist of only a question whereas training data do a pair of question and answer. Thus they cannot provide enough information for good classification in many cases. Since the answer is strongly associated with the input questions, we try to create a pseudo answer to expand each input question. Translation probabilities between questions and answers and a pseudo relevant feedback technique are used to generate the pseudo answer. As a result, we obtain the significant improved performances when two approaches are effectively combined.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2015DAL0005/_p
Copy
@ARTICLE{e99-d_4_1019,
author={Kyoungman BAE, Youngjoong KO, },
journal={IEICE TRANSACTIONS on Information},
title={How to Combine Translation Probabilities and Question Expansion for Question Classification in cQA Services},
year={2016},
volume={E99-D},
number={4},
pages={1019-1022},
abstract={This paper claims to use a new question expansion method for question classification in cQA services. The input questions consist of only a question whereas training data do a pair of question and answer. Thus they cannot provide enough information for good classification in many cases. Since the answer is strongly associated with the input questions, we try to create a pseudo answer to expand each input question. Translation probabilities between questions and answers and a pseudo relevant feedback technique are used to generate the pseudo answer. As a result, we obtain the significant improved performances when two approaches are effectively combined.},
keywords={},
doi={10.1587/transinf.2015DAL0005},
ISSN={1745-1361},
month={April},}
Copy
TY - JOUR
TI - How to Combine Translation Probabilities and Question Expansion for Question Classification in cQA Services
T2 - IEICE TRANSACTIONS on Information
SP - 1019
EP - 1022
AU - Kyoungman BAE
AU - Youngjoong KO
PY - 2016
DO - 10.1587/transinf.2015DAL0005
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E99-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2016
AB - This paper claims to use a new question expansion method for question classification in cQA services. The input questions consist of only a question whereas training data do a pair of question and answer. Thus they cannot provide enough information for good classification in many cases. Since the answer is strongly associated with the input questions, we try to create a pseudo answer to expand each input question. Translation probabilities between questions and answers and a pseudo relevant feedback technique are used to generate the pseudo answer. As a result, we obtain the significant improved performances when two approaches are effectively combined.
ER -
English
