Abstract
Named Entity Recognisers (NERs) are typically used by question answering (QA) systems as means to preselect answer candidates. However, there has not been much work on the formal assessment of the use of NERs for QA nor on their optimal parameters. In this paper we investigate the main characteristics of a NER for QA. The results show that it is important to maintain high recall to retain all possible answers on the one hand, while high precision is essential during the final answer selection phase. We present an NER designed for QA, which aims at having a
high recall.
Original language | English |
---|---|
Title of host publication | Proceedings of the 10th Conference of the Pacific Association for Computational Linguistics, PACLING 2007 |
Editors | Timothy Baldwin, David Martinez |
Publisher | Pacific Association for Computational Linguistics |
Pages | 317-324 |
Number of pages | 8 |
Publication status | Published - 2007 |
Event | Conference of the Pacific Association for Computational Linguistics (10th : 2007) - Melbourne Duration: 19 Sep 2007 → 21 Sep 2007 |
Conference
Conference | Conference of the Pacific Association for Computational Linguistics (10th : 2007) |
---|---|
City | Melbourne |
Period | 19/09/07 → 21/09/07 |
Bibliographical note
Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.Keywords
- named entity recognition
- question answering
- text processing
- computational linguistics