A pattern learning approach to question answering within the Ephyra framework (2006)
| Venue: | Proceedings of the Ninth International Conference on TEXT, SPEECH and DIALOGUE |
| Citations: | 7 - 3 self |
BibTeX
@INPROCEEDINGS{Schlaefer06apattern,
author = {Nico Schlaefer and Petra Gieselmann and Thomas Schaaf},
title = {A pattern learning approach to question answering within the Ephyra framework},
booktitle = {Proceedings of the Ninth International Conference on TEXT, SPEECH and DIALOGUE},
year = {2006}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
Abstract. This paper describes the Ephyra question answering engine, a modular and extensible framework that allows to integrate multiple approaches to question answering in one system. Our framework can be adapted to languages other than English by replacing language-specific components. It supports the two major approaches to question answering, knowledge annotation and knowledge mining. Ephyra uses the web as a data resource, but could also work with smaller corpora. In addition, we propose a novel approach to question interpretation which abstracts from the original formulation of the question. Text patterns are used to interpret a question and to extract answers from text snippets. Our system automatically learns the patterns for answer extraction, using question-answer pairs as training data. Experimental results revealed the potential of this approach. 1
Citations
| 130 | Data-intensive question answering - Brill, Lin, et al. - 2001 |
| 108 | The TREC-8 Question Answering Track Evaluation - Voorhees, Tice - 2000 |
| 40 | Question Answering from the Web Using Knowledge Annotation and Knowledge Mining Techniques - Lin, Katz |
| 30 | AnswerBus question answering system - ZHENG |
| 10 | Web based pattern mining and matching approach to question answering - Zhang, Lee - 2002 |
| 1 | L.: The 14 th Text REtrieval - Voorhees, Buckland - 2005 |
