A Named entity recogniser for question answering

Menno van Zaanen; Diego Mollá

A Named entity recogniser for question answering

Menno van Zaanen, Diego Mollá

School of Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

11 Downloads (Pure)

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

Access to Document

Mq-11066-Publisher version (open access)Final published version, 136 KBLicence: Unspecified

Cite this

@inproceedings{09e6e2e81d374adb96b687cbc4b9c4b2,

title = "A Named entity recogniser for question answering",

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.",

keywords = "named entity recognition, question answering, text processing, computational linguistics",

author = "{van Zaanen}, Menno and Diego Moll{\'a}",

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.; Conference of the Pacific Association for Computational Linguistics (10th : 2007) ; Conference date: 19-09-2007 Through 21-09-2007",

year = "2007",

language = "English",

pages = "317--324",

editor = "Timothy Baldwin and David Martinez",

booktitle = "Proceedings of the 10th Conference of the Pacific Association for Computational Linguistics, PACLING 2007",

publisher = "Pacific Association for Computational Linguistics",

}

van Zaanen, M & Mollá, D 2007, A Named entity recogniser for question answering. in T Baldwin & D Martinez (eds), Proceedings of the 10th Conference of the Pacific Association for Computational Linguistics, PACLING 2007. Pacific Association for Computational Linguistics, pp. 317-324, Conference of the Pacific Association for Computational Linguistics (10th : 2007), Melbourne, 19/09/07.

A Named entity recogniser for question answering. / van Zaanen, Menno; Mollá, Diego.

Proceedings of the 10th Conference of the Pacific Association for Computational Linguistics, PACLING 2007. ed. / Timothy Baldwin; David Martinez. Pacific Association for Computational Linguistics, 2007. p. 317-324.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

TY - GEN

T1 - A Named entity recogniser for question answering

AU - van Zaanen, Menno

AU - Mollá, Diego

N1 - 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.

PY - 2007

Y1 - 2007

N2 - 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.

AB - 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.

KW - named entity recognition

KW - question answering

KW - text processing

KW - computational linguistics

M3 - Conference proceeding contribution

SP - 317

EP - 324

BT - Proceedings of the 10th Conference of the Pacific Association for Computational Linguistics, PACLING 2007

A2 - Baldwin, Timothy

A2 - Martinez, David

PB - Pacific Association for Computational Linguistics

T2 - Conference of the Pacific Association for Computational Linguistics (10th : 2007)

Y2 - 19 September 2007 through 21 September 2007

ER -