Finding needles in the haystack: Search and candidate generation

被引：9

作者：

Chu-Carroll, J. ^{[1
]}

Fan, J. ^{[1
]}

Boguraev, B. K. ^{[1
]}

Carmel, D. ^{[2
]}

Sheinwald, D. ^{[2
]}

Welty, C. ^{[1
]}

机构：

[1] IBM Corp, Div Res, Thomas J Watson Res Ctr, Yorktown Hts, NY 10598 USA

[2] IBM Res Div, Haifa Res Lab, IL-31905 Haifa, Israel

来源：

IBM JOURNAL OF RESEARCH AND DEVELOPMENT | 2012年 / 56卷 / 3-4期

关键词：

D O I：

10.1147/JRD.2012.2186682

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

080201 [机械制造及其自动化];

摘要：

A key phase in the DeepQA architecture is Hypothesis Generation, in which candidate system responses are generated for downstream scoring and ranking. In the IBM Watson (TM) system, these hypotheses are potential answers to Jeopardy!(TM) questions and are generated by two components: search and candidate generation. The search component retrieves content relevant to a given question from Watson's knowledge resources. The candidate generation component identifies potential answers to the question from the retrieved content. In this paper, we present strategies developed to use characteristics of Watson's different knowledge sources and to formulate effective search queries against those sources. We further discuss a suite of candidate generation strategies that use various kinds of metadata, such as document titles or anchor texts in hyperlinked documents. We demonstrate that a combination of these strategies brings the correct answer into the candidate answer pool for 87.17% of all the questions in a blind test set, facilitating high end-to-end question-answering performance.

引用

页数：12

共 34 条

[21]

Katz B., 2005, 14 ANN TEXT RETRIEVA

[22]

Katz B., 2003, P ASS COMPUTATIONAL, P426

[23]

Katz B., 2000, P ACL WORKSH REC ADV, P67

[24]

Kupiec J., 1993, SIGIR Forum, P181

[25]

Question analysis: How Watson reads a clue [J].

Lally, A. ;

Prager, J. M. ;

McCord, M. C. ;

Boguraev, B. K. ;

Patwardhan, S. ;

Fan, J. ;

Fodor, P. ;

Chu-Carroll, J. .

IBM JOURNAL OF RESEARCH AND DEVELOPMENT, 2012, 56 (3-4)

[26]

Magnini B, 2002, 40TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, PROCEEDINGS OF THE CONFERENCE, P425

[27]

Combining the language model and inference network approaches to retrieval [J].

Metzler, D ;

Croft, WB .

INFORMATION PROCESSING & MANAGEMENT, 2004, 40 (05) :735-750

[28]

Moldovan D, 2000, 38TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, PROCEEDINGS OF THE CONFERENCE, P563

[29]

Murdock J. W., 2012, IBM J RES DEV, V56, P8

[30]

Prager J., 2000, SIGIR Forum, V34, P184

← 1 2 3 4 →