ACM Home Page
Please provide us with feedback. Feedback
High performance question/answering
Full text PdfPdf (256 KB)
Source Annual ACM Conference on Research and Development in Information Retrieval archive
Proceedings of the 24th annual international ACM SIGIR conference on Research and development in information retrieval table of contents
New Orleans, Louisiana, United States
Pages: 366 - 374  
Year of Publication: 2001
ISBN:1-58113-331-6
Authors
Marius A. Pasca  Southern Methodist Univ., Dallas, TX
Sandra M. Harabagiu  Univ. of Texas at Austin, Austin
Sponsor
SIGIR: ACM Special Interest Group on Information Retrieval
Publisher
ACM  New York, NY, USA
Bibliometrics
Downloads (6 Weeks): 10,   Downloads (12 Months): 78,   Citation Count: 30
Additional Information:

abstract   references   cited by   index terms   collaborative colleagues  

Tools and Actions: Request Permissions Request Permissions    Review this Article  
DOI Bookmark: Use this link to bookmark this Article: http://doi.acm.org/10.1145/383952.384025
What is a DOI?

ABSTRACT

In this paper we present the features of a Question/Answering (Q/A) system that had unparalleled performance in the TREC-9 evaluations. We explain the accuracy of our system through the unique characteristics of its architecture: (1) usage of a wide-coverage answer type taxonomy; (2) repeated passage retrieval; (3) lexico-semantic feedback loops; (4) extraction of the answers based on machine learning techniques; and (5) answer caching. Experimental results show the effects of each feature on the overall performance of the Q/A system and lead to general conclusions about Q/A from large text collections.


REFERENCES

Note: OCR errors may be found in this Reference List extracted from the full text article. ACM has opted to expose the complete List rather than only correct and linked references.

 
1
 
2
P. Cohen, R. Schrag, E. Jones, A. Pease, A. Lin, B. Starr, D. Easter, D. Gunning, and M. Burke. The DARPA High Performance Knowledge Bases Project. Artificial Intelligence Magazine, 19(4):25-49, 1998.
 
3
 
4
A. Graesser and S. Gordon. Question-Answering and the Organization of World Knowledge, chapter Question-Answering and the Organization of World Knowledge. Lawrence Erlbaum, 1991.
 
5
S. Harabagiu and S. Maiorano. Finding answers in large collections of texts: Paragraph indexing + abductive inference. In AAAI Fall Symposium on Question Answering Systems, pages 63-71, November 1999.
 
6
 
7
B. Katz. From sentence processing to information access on the world wide web. In AAAI Spring Symposium on Natural Language Processing for the World Wide Web, Stanford, California, 1997.
 
8
W. Lehnert. The Process of Question Answering: a computer simulation of cognition. Lawrence Erlbaum, 1978.
9
 
10
D. Moldovan, S. Harabagiu, M. Pacsca, R. Mihalcea, R. Goodrum, R. Girju, and V. Rus. LASSO: a tool for surfing the answer net. In Proceedings of the 8th TExt Retrieval Conference (TREC-8), Gaithersburg, Maryland, 1999. NIST.
 
11
J. Prager, D. Radev, E. Brown, A. Coden, and V. Samn. The use of predictive annotation for question answering in TREC8. In Proceedings of the 8th TExt Retrieval Conference (TREC-8), Gaithersburg, Maryland, 1999. NIST.
 
12
G. Salton, editor. The SMART Retrieval System. Prentice-Hall, New Jersey, 1969.
 
13
R. Srihari and W. Li. Question answering supported by information extraction. In Proceedings of the 8th TExt Retrieval Conference (TREC-8), Gaithersburg, Maryland, 1999. NIST.
 
14
T. Winograd. Five lectures on artificial intelligence. Linguistic Structures Processing. In Fundamental Studies in Computer Science, 5:399-520, 1977.
 
15
W. Woods and R. Kaplan. Lunar rocks in natural English: Explorations in natural language question answering. Linguistic Structures Processing. In Fundamental Studies in Computer Science, 5:521-569, 1977.

CITED BY  30

Collaborative Colleagues:
Marius A. Pasca: colleagues
Sandra M. Harabagiu: colleagues