Evaluating Retrieval Performance for Japanese Question Answering

What Are Best Passages?

Tetsuya Sakai, Tomoharu Kokubu

Research output: Contribution to journalArticle

Abstract

A document retrieval test collection was automatically generated from the QAC1 (Question Answering Challenge 1) Question Answering test collection. The BRIDJE system, using the Okapi/BM25 term weighing, was used for document retrieval. For retrieval performance evaluation, the 1998 portion of the QAC1 collection was converted into a document retrieval test collection by regarding the Task 1 questions as search requests. The retrieval performance of three different passage types were compared.

Original languageEnglish
Pages (from-to)429-430
Number of pages2
JournalSIGIR Forum (ACM Special Interest Group on Information Retrieval)
Issue numberSPEC. ISS.
Publication statusPublished - 2003
Externally publishedYes

Fingerprint

Weighing
Question answering
Test collections

Keywords

  • Passage Retrieval
  • Question Answering

ASJC Scopus subject areas

  • Hardware and Architecture
  • Management Information Systems

Cite this

Evaluating Retrieval Performance for Japanese Question Answering : What Are Best Passages? / Sakai, Tetsuya; Kokubu, Tomoharu.

In: SIGIR Forum (ACM Special Interest Group on Information Retrieval), No. SPEC. ISS., 2003, p. 429-430.

Research output: Contribution to journalArticle

@article{25b857abbb964374b230761edece9ade,
title = "Evaluating Retrieval Performance for Japanese Question Answering: What Are Best Passages?",
abstract = "A document retrieval test collection was automatically generated from the QAC1 (Question Answering Challenge 1) Question Answering test collection. The BRIDJE system, using the Okapi/BM25 term weighing, was used for document retrieval. For retrieval performance evaluation, the 1998 portion of the QAC1 collection was converted into a document retrieval test collection by regarding the Task 1 questions as search requests. The retrieval performance of three different passage types were compared.",
keywords = "Passage Retrieval, Question Answering",
author = "Tetsuya Sakai and Tomoharu Kokubu",
year = "2003",
language = "English",
pages = "429--430",
journal = "SIGIR Forum (ACM Special Interest Group on Information Retrieval)",
issn = "0163-5840",
publisher = "Association for Computing Machinery (ACM)",
number = "SPEC. ISS.",

}

TY - JOUR

T1 - Evaluating Retrieval Performance for Japanese Question Answering

T2 - What Are Best Passages?

AU - Sakai, Tetsuya

AU - Kokubu, Tomoharu

PY - 2003

Y1 - 2003

N2 - A document retrieval test collection was automatically generated from the QAC1 (Question Answering Challenge 1) Question Answering test collection. The BRIDJE system, using the Okapi/BM25 term weighing, was used for document retrieval. For retrieval performance evaluation, the 1998 portion of the QAC1 collection was converted into a document retrieval test collection by regarding the Task 1 questions as search requests. The retrieval performance of three different passage types were compared.

AB - A document retrieval test collection was automatically generated from the QAC1 (Question Answering Challenge 1) Question Answering test collection. The BRIDJE system, using the Okapi/BM25 term weighing, was used for document retrieval. For retrieval performance evaluation, the 1998 portion of the QAC1 collection was converted into a document retrieval test collection by regarding the Task 1 questions as search requests. The retrieval performance of three different passage types were compared.

KW - Passage Retrieval

KW - Question Answering

UR - http://www.scopus.com/inward/record.url?scp=1542377479&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1542377479&partnerID=8YFLogxK

M3 - Article

SP - 429

EP - 430

JO - SIGIR Forum (ACM Special Interest Group on Information Retrieval)

JF - SIGIR Forum (ACM Special Interest Group on Information Retrieval)

SN - 0163-5840

IS - SPEC. ISS.

ER -