Question Answering for Dutch: Simple does it

A.H. Hoekstra; Djoerd Hiemstra; P.E. van der Vet; Theo W.C. Huibers

Question Answering for Dutch: Simple does it

A.H. Hoekstra, Djoerd Hiemstra, P.E. van der Vet, Theo W.C. Huibers

Databases (Former)

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

1 Citation (Scopus)

72 Downloads (Pure)

Abstract

When people pose questions in natural language to search for information on the web, the role of question answering (QA) systems becomes important. In this paper the QAsystem simpleQA, capable of answering Dutch questions on which the answer is a person or a location, is described. The system's algorithm does not use a lot of complex NLP-techniques, but instead uses the magnitude of and redundancy on the World Wide Web to its advantage. The system has been evaluated on the DISEQuA corpus and performed quite well: MRR near 0.5. For further improvements it can easily be extended by adding more rewrite rules and applying more sophisticated filtering and tiling.

Original language	English
Title of host publication	BNAIC’06
Subtitle of host publication	Proceedings of the 18th Belgium-Netherlands Conference on Artificial Intelligence
Editors	Pierre-Yves Schobbens, Wim Vanhoof, Gabriel Schwanen
Publisher	Namur University Press
Pages	179-186
Number of pages	8
Publication status	Published - 2006
Event	18th Belgium-Dutch Conference on Artificial Intelligence, BNAIC 2006 - Namur, Belgium Duration: 5 Oct 2006 → 6 Oct 2006 Conference number: 18 https://staff.info.unamur.be/wva/BNAIC06/index.php

Publication series

Name	Belgian-Dutch Conference on Artificial Intelligence
Volume	2006
ISSN (Print)	1568-7805

Conference

Conference	18th Belgium-Dutch Conference on Artificial Intelligence, BNAIC 2006
Abbreviated title	BNAIC
Country/Territory	Belgium
City	Namur
Period	5/10/06 → 6/10/06
Internet address	https://staff.info.unamur.be/wva/BNAIC06/index.php

Keywords

IR-66748
METIS-237815
EWI-8645

Access to Document

bnaic06

https://staff.info.unamur.be/~wva/BNAIC06/proceedings.php

Cite this

Hoekstra, A. H., Hiemstra, D., van der Vet, P. E., & Huibers, T. W. C. (2006). Question Answering for Dutch: Simple does it. In P-Y. Schobbens, W. Vanhoof, & G. Schwanen (Eds.), BNAIC’06: Proceedings of the 18th Belgium-Netherlands Conference on Artificial Intelligence (pp. 179-186). (Belgian-Dutch Conference on Artificial Intelligence; Vol. 2006). Namur University Press. https://staff.info.unamur.be/~wva/BNAIC06/proceedings.php

@inproceedings{e64da51168454640a26cdbda940ed19c,

title = "Question Answering for Dutch: Simple does it",

abstract = "When people pose questions in natural language to search for information on the web, the role of question answering (QA) systems becomes important. In this paper the QAsystem simpleQA, capable of answering Dutch questions on which the answer is a person or a location, is described. The system's algorithm does not use a lot of complex NLP-techniques, but instead uses the magnitude of and redundancy on the World Wide Web to its advantage. The system has been evaluated on the DISEQuA corpus and performed quite well: MRR near 0.5. For further improvements it can easily be extended by adding more rewrite rules and applying more sophisticated filtering and tiling.",

keywords = "IR-66748, METIS-237815, EWI-8645",

author = "A.H. Hoekstra and Djoerd Hiemstra and {van der Vet}, P.E. and Huibers, {Theo W.C.}",

year = "2006",

language = "English",

series = "Belgian-Dutch Conference on Artificial Intelligence",

publisher = "Namur University Press",

pages = "179--186",

editor = "Pierre-Yves Schobbens and Wim Vanhoof and Gabriel Schwanen",

booktitle = "BNAIC{\textquoteright}06",

note = "18th Belgium-Dutch Conference on Artificial Intelligence, BNAIC 2006, BNAIC ; Conference date: 05-10-2006 Through 06-10-2006",

url = "https://staff.info.unamur.be/wva/BNAIC06/index.php",

}

Hoekstra, AH, Hiemstra, D, van der Vet, PE & Huibers, TWC 2006, Question Answering for Dutch: Simple does it. in P-Y Schobbens, W Vanhoof & G Schwanen (eds), BNAIC’06: Proceedings of the 18th Belgium-Netherlands Conference on Artificial Intelligence. Belgian-Dutch Conference on Artificial Intelligence, vol. 2006, Namur University Press, pp. 179-186, 18th Belgium-Dutch Conference on Artificial Intelligence, BNAIC 2006, Namur, Belgium, 5/10/06. <https://staff.info.unamur.be/~wva/BNAIC06/proceedings.php>

Question Answering for Dutch: Simple does it. / Hoekstra, A.H.; Hiemstra, Djoerd; van der Vet, P.E. et al.
BNAIC’06: Proceedings of the 18th Belgium-Netherlands Conference on Artificial Intelligence. ed. / Pierre-Yves Schobbens; Wim Vanhoof; Gabriel Schwanen. Namur University Press, 2006. p. 179-186 (Belgian-Dutch Conference on Artificial Intelligence; Vol. 2006).

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

TY - GEN

T1 - Question Answering for Dutch

T2 - 18th Belgium-Dutch Conference on Artificial Intelligence, BNAIC 2006

AU - Hoekstra, A.H.

AU - Hiemstra, Djoerd

AU - van der Vet, P.E.

AU - Huibers, Theo W.C.

N1 - Conference code: 18

PY - 2006

Y1 - 2006

N2 - When people pose questions in natural language to search for information on the web, the role of question answering (QA) systems becomes important. In this paper the QAsystem simpleQA, capable of answering Dutch questions on which the answer is a person or a location, is described. The system's algorithm does not use a lot of complex NLP-techniques, but instead uses the magnitude of and redundancy on the World Wide Web to its advantage. The system has been evaluated on the DISEQuA corpus and performed quite well: MRR near 0.5. For further improvements it can easily be extended by adding more rewrite rules and applying more sophisticated filtering and tiling.

AB - When people pose questions in natural language to search for information on the web, the role of question answering (QA) systems becomes important. In this paper the QAsystem simpleQA, capable of answering Dutch questions on which the answer is a person or a location, is described. The system's algorithm does not use a lot of complex NLP-techniques, but instead uses the magnitude of and redundancy on the World Wide Web to its advantage. The system has been evaluated on the DISEQuA corpus and performed quite well: MRR near 0.5. For further improvements it can easily be extended by adding more rewrite rules and applying more sophisticated filtering and tiling.

KW - IR-66748

KW - METIS-237815

KW - EWI-8645

M3 - Conference contribution

T3 - Belgian-Dutch Conference on Artificial Intelligence

SP - 179

EP - 186

BT - BNAIC’06

A2 - Schobbens, Pierre-Yves

A2 - Vanhoof, Wim

A2 - Schwanen, Gabriel

PB - Namur University Press

Y2 - 5 October 2006 through 6 October 2006

ER -

Question Answering for Dutch: Simple does it

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this