SHAPAQA: Shallow Parsing for Question Answering on the World Wide Web

S. Buchholz; W. Daelemans

SHAPAQA: Shallow Parsing for Question Answering on the World Wide Web

S. Buchholz, W. Daelemans

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

87 Downloads (Pure)

Abstract

We introduce shapaqa, a shallow parsing approach to online, open-domain question answering on the WorldWideWeb. Given a form-based natural language question as input, the system uses a memory-based shallow parser to analyze web pages retrieved using normal keyword search on a search engine. Two versions of the system are evaluated on a test set of 200 questions. In combination with two back-off methods a mean reciprocal rank of .46 is achieved.

Original language	English
Title of host publication	Proceedings Euroconference
Subtitle of host publication	Recent Advances in Natural Language Processing, Tsigov Chark, Bulgaria, 5-7 September 2001
Editors	G. Angelova, et al.
Place of Publication	Bulgaria
Publisher	Tsigov Chark
Pages	47-51
Number of pages	5
ISBN (Print)	9789549090611
Publication status	Published - 2001

Access to Document

Buchholz shapaqa

Cite this

@inproceedings{9def3cf95ac341c9be17d1ecbe15e264,

title = "SHAPAQA: Shallow Parsing for Question Answering on the World Wide Web",

abstract = "We introduce shapaqa, a shallow parsing approach to online, open-domain question answering on the WorldWideWeb. Given a form-based natural language question as input, the system uses a memory-based shallow parser to analyze web pages retrieved using normal keyword search on a search engine. Two versions of the system are evaluated on a test set of 200 questions. In combination with two back-off methods a mean reciprocal rank of .46 is achieved.",

author = "S. Buchholz and W. Daelemans",

note = "Pagination: 5",

year = "2001",

language = "English",

isbn = "9789549090611",

pages = "47--51",

editor = "G. Angelova and {et al.}",

booktitle = "Proceedings Euroconference",

publisher = "Tsigov Chark",

}

SHAPAQA: Shallow Parsing for Question Answering on the World Wide Web. / Buchholz, S.; Daelemans, W.
Proceedings Euroconference: Recent Advances in Natural Language Processing, Tsigov Chark, Bulgaria, 5-7 September 2001. ed. / G. Angelova; et al. Bulgaria: Tsigov Chark, 2001. p. 47-51.

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

TY - GEN

T1 - SHAPAQA

T2 - Shallow Parsing for Question Answering on the World Wide Web

AU - Buchholz, S.

AU - Daelemans, W.

N1 - Pagination: 5

PY - 2001

Y1 - 2001

N2 - We introduce shapaqa, a shallow parsing approach to online, open-domain question answering on the WorldWideWeb. Given a form-based natural language question as input, the system uses a memory-based shallow parser to analyze web pages retrieved using normal keyword search on a search engine. Two versions of the system are evaluated on a test set of 200 questions. In combination with two back-off methods a mean reciprocal rank of .46 is achieved.

AB - We introduce shapaqa, a shallow parsing approach to online, open-domain question answering on the WorldWideWeb. Given a form-based natural language question as input, the system uses a memory-based shallow parser to analyze web pages retrieved using normal keyword search on a search engine. Two versions of the system are evaluated on a test set of 200 questions. In combination with two back-off methods a mean reciprocal rank of .46 is achieved.

M3 - Conference contribution

SN - 9789549090611

SP - 47

EP - 51

BT - Proceedings Euroconference

A2 - Angelova, G.

A2 - et al., null

PB - Tsigov Chark

CY - Bulgaria

ER -

SHAPAQA: Shallow Parsing for Question Answering on the World Wide Web

Abstract

Access to Document

Fingerprint

Cite this