Learning surface text patterns for a Question Answering system
D. Ravichandran, and E. Hovy. Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, page 41--47. Stroudsburg, PA, USA, Association for Computational Linguistics, (2002)
DOI: 10.3115/1073083.1073092
Abstract
In this paper we explore the power of surface text patterns for open-domain question answering systems. In order to obtain an optimal set of patterns, we have developed a method for learning such patterns automatically. A tagged corpus is built from the Internet in a bootstrapping process by providing a few hand-crafted examples of each question type to Altavista. Patterns are then automatically extracted from the returned documents and standardized. We calculate the precision of each pattern, and the average precision for each question type. These patterns are then applied to find answers to new questions. Using the TREC-10 question set, we report results for two cases: answers determined from the TREC-10 corpus and from the web.
Description
Learning surface text patterns for a Question Answering system
%0 Conference Paper
%1 Ravichandran:2002:LST:1073083.1073092
%A Ravichandran, Deepak
%A Hovy, Eduard
%B Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
%C Stroudsburg, PA, USA
%D 2002
%I Association for Computational Linguistics
%K precision question-answering_systems text_patterns
%P 41--47
%R 10.3115/1073083.1073092
%T Learning surface text patterns for a Question Answering system
%U http://dx.doi.org/10.3115/1073083.1073092
%X In this paper we explore the power of surface text patterns for open-domain question answering systems. In order to obtain an optimal set of patterns, we have developed a method for learning such patterns automatically. A tagged corpus is built from the Internet in a bootstrapping process by providing a few hand-crafted examples of each question type to Altavista. Patterns are then automatically extracted from the returned documents and standardized. We calculate the precision of each pattern, and the average precision for each question type. These patterns are then applied to find answers to new questions. Using the TREC-10 question set, we report results for two cases: answers determined from the TREC-10 corpus and from the web.
@inproceedings{Ravichandran:2002:LST:1073083.1073092,
abstract = {In this paper we explore the power of surface text patterns for open-domain question answering systems. In order to obtain an optimal set of patterns, we have developed a method for learning such patterns automatically. A tagged corpus is built from the Internet in a bootstrapping process by providing a few hand-crafted examples of each question type to Altavista. Patterns are then automatically extracted from the returned documents and standardized. We calculate the precision of each pattern, and the average precision for each question type. These patterns are then applied to find answers to new questions. Using the TREC-10 question set, we report results for two cases: answers determined from the TREC-10 corpus and from the web.},
acmid = {1073092},
added-at = {2011-06-20T12:06:32.000+0200},
address = {Stroudsburg, PA, USA},
author = {Ravichandran, Deepak and Hovy, Eduard},
biburl = {https://www.bibsonomy.org/bibtex/2cec6e340cfad718f56000428075310ef/jennymac},
booktitle = {Proceedings of the 40th Annual Meeting on Association for Computational Linguistics},
description = {Learning surface text patterns for a Question Answering system},
doi = {10.3115/1073083.1073092},
interhash = {e523f02cfc750ce0140e222fe006aaa8},
intrahash = {cec6e340cfad718f56000428075310ef},
keywords = {precision question-answering_systems text_patterns},
location = {Philadelphia, Pennsylvania},
numpages = {7},
pages = {41--47},
publisher = {Association for Computational Linguistics},
series = {ACL '02},
timestamp = {2011-06-20T12:06:32.000+0200},
title = {Learning surface text patterns for a Question Answering system},
url = {http://dx.doi.org/10.3115/1073083.1073092},
year = 2002
}