Use of Dynamic Passage Selection and Lexico-Semantic Patterns for Japanese Natural Language Question Answering

Seungwoo LEE; Gary Geunbae LEE

Use of Dynamic Passage Selection and Lexico-Semantic Patterns for Japanese Natural Language Question Answering

Seungwoo LEE, Gary Geunbae LEE

Full Text Views

0

Share
Cite this

Summary :

This paper describes a practical Japanese natural language Question Answering system adopting effective selection of dynamic passages, Lexico-Semantic Patterns (LSP), and Predictive Answer Indexing. By analyzing the previous TREC QA data, we defined a dynamic passage unit and developed a passage selection method suitable for Question Answering. Using LSP, we identify the answer type of a question and detect answer candidates without any deep linguistic analyses of the texts. To guarantee a short response time, Predictive Answer Indexing is combined into our overall system architecture. As a result of the three engineering techniques, our system showed excellent performance when evaluated by mean reciprocal rank (MRR) in NTCIR-3 QAC-1.

Publication: IEICE TRANSACTIONS on Information Vol.E86-D No.9 pp.1638-1647

Publication Date: 2003/09/01

Publicized

Online ISSN

DOI

Type of Manuscript: Special Section PAPER (Special Issue on Text Processing for Information Access)

Category

Cite this

Copy

Seungwoo LEE, Gary Geunbae LEE, "Use of Dynamic Passage Selection and Lexico-Semantic Patterns for Japanese Natural Language Question Answering" in IEICE TRANSACTIONS on Information, vol. E86-D, no. 9, pp. 1638-1647, September 2003, doi: .
Abstract: This paper describes a practical Japanese natural language Question Answering system adopting effective selection of dynamic passages, Lexico-Semantic Patterns (LSP), and Predictive Answer Indexing. By analyzing the previous TREC QA data, we defined a dynamic passage unit and developed a passage selection method suitable for Question Answering. Using LSP, we identify the answer type of a question and detect answer candidates without any deep linguistic analyses of the texts. To guarantee a short response time, Predictive Answer Indexing is combined into our overall system architecture. As a result of the three engineering techniques, our system showed excellent performance when evaluated by mean reciprocal rank (MRR) in NTCIR-3 QAC-1.
URL: https://globals.ieice.org/en_transactions/information/10.1587/e86-d_9_1638/_p

Copy

@ARTICLE{e86-d_9_1638,
author={Seungwoo LEE, Gary Geunbae LEE, },
journal={IEICE TRANSACTIONS on Information},
title={Use of Dynamic Passage Selection and Lexico-Semantic Patterns for Japanese Natural Language Question Answering},
year={2003},
volume={E86-D},
number={9},
pages={1638-1647},
abstract={This paper describes a practical Japanese natural language Question Answering system adopting effective selection of dynamic passages, Lexico-Semantic Patterns (LSP), and Predictive Answer Indexing. By analyzing the previous TREC QA data, we defined a dynamic passage unit and developed a passage selection method suitable for Question Answering. Using LSP, we identify the answer type of a question and detect answer candidates without any deep linguistic analyses of the texts. To guarantee a short response time, Predictive Answer Indexing is combined into our overall system architecture. As a result of the three engineering techniques, our system showed excellent performance when evaluated by mean reciprocal rank (MRR) in NTCIR-3 QAC-1.},
keywords={},
doi={},
ISSN={},
month={September},}

Copy

TY - JOUR
TI - Use of Dynamic Passage Selection and Lexico-Semantic Patterns for Japanese Natural Language Question Answering
T2 - IEICE TRANSACTIONS on Information
SP - 1638
EP - 1647
AU - Seungwoo LEE
AU - Gary Geunbae LEE
PY - 2003
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E86-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2003
AB - This paper describes a practical Japanese natural language Question Answering system adopting effective selection of dynamic passages, Lexico-Semantic Patterns (LSP), and Predictive Answer Indexing. By analyzing the previous TREC QA data, we defined a dynamic passage unit and developed a passage selection method suitable for Question Answering. Using LSP, we identify the answer type of a question and detect answer candidates without any deep linguistic analyses of the texts. To guarantee a short response time, Predictive Answer Indexing is combined into our overall system architecture. As a result of the three engineering techniques, our system showed excellent performance when evaluated by mean reciprocal rank (MRR) in NTCIR-3 QAC-1.
ER -