Cross-Lingual Question Answering Using Off-the-Shelf Machine Translation

Kisuh Ahn; Beatrice Alex; Johan Bos; Tiphaine Dalmas; Jochen L. Leidner; Matthew B. Smillie

doi:10.1007/11519645_44

Cross-Lingual Question Answering Using Off-the-Shelf Machine Translation

Kisuh Ahn, Beatrice Alex, Johan Bos, Tiphaine Dalmas, Jochen L. Leidner, Matthew B. Smillie

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

Abstract / Description of output

We show how to adapt an existing monolingual open-domain QA system to perform in a cross-lingual environment, using off-the-shelf machine translation software. In our experiments we use French and German as source language, and English as target language. For answering factoid questions, our system performs with an accuracy of 16% (German to English) and 20% (French to English), respectively. The loss of correctly answered questions caused by the MT component is estimated at 10% for French, and 15% for German. The accuracy of our system on correctly translated questions is 28% for German and 29% for French.

Original language	English
Title of host publication	Multilingual Information Access for Text, Speech and Images
Subtitle of host publication	5th Workshop of the Cross-Language Evaluation Forum, CLEF 2004, Bath, UK, September 15-17, 2004, Revised Selected Papers
Publisher	Springer
Pages	446-457
Number of pages	12
ISBN (Electronic)	978-3-540-32051-7
ISBN (Print)	978-3-540-27420-9
DOIs	https://doi.org/10.1007/11519645_44
Publication status	Published - 2005

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer Berlin Heidelberg
Volume	3491
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Access to Document

10.1007/11519645_44

http://link.springer.com/chapter/10.1007%2F11519645_44

Stanford Strategic Alliance
Grover, C.
UK central government bodies/local authorities, health and hospital authorities
1/10/02 → 30/09/04
Project: Research

Cite this

Ahn, K., Alex, B., Bos, J., Dalmas, T., Leidner, J. L., & Smillie, M. B. (2005). Cross-Lingual Question Answering Using Off-the-Shelf Machine Translation. In Multilingual Information Access for Text, Speech and Images: 5th Workshop of the Cross-Language Evaluation Forum, CLEF 2004, Bath, UK, September 15-17, 2004, Revised Selected Papers (pp. 446-457). (Lecture Notes in Computer Science; Vol. 3491). Springer. https://doi.org/10.1007/11519645_44

Ahn, Kisuh ; Alex, Beatrice ; Bos, Johan et al. / Cross-Lingual Question Answering Using Off-the-Shelf Machine Translation. Multilingual Information Access for Text, Speech and Images: 5th Workshop of the Cross-Language Evaluation Forum, CLEF 2004, Bath, UK, September 15-17, 2004, Revised Selected Papers. Springer, 2005. pp. 446-457 (Lecture Notes in Computer Science).

@inproceedings{5c90210f4fed4031a8f2fe57c8e808c6,

title = "Cross-Lingual Question Answering Using Off-the-Shelf Machine Translation",

abstract = "We show how to adapt an existing monolingual open-domain QA system to perform in a cross-lingual environment, using off-the-shelf machine translation software. In our experiments we use French and German as source language, and English as target language. For answering factoid questions, our system performs with an accuracy of 16% (German to English) and 20% (French to English), respectively. The loss of correctly answered questions caused by the MT component is estimated at 10% for French, and 15% for German. The accuracy of our system on correctly translated questions is 28% for German and 29% for French.",

author = "Kisuh Ahn and Beatrice Alex and Johan Bos and Tiphaine Dalmas and Leidner, {Jochen L.} and Smillie, {Matthew B.}",

year = "2005",

doi = "10.1007/11519645_44",

language = "English",

isbn = "978-3-540-27420-9",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "446--457",

booktitle = "Multilingual Information Access for Text, Speech and Images",

address = "United Kingdom",

}

Ahn, K, Alex, B, Bos, J, Dalmas, T, Leidner, JL & Smillie, MB 2005, Cross-Lingual Question Answering Using Off-the-Shelf Machine Translation. in Multilingual Information Access for Text, Speech and Images: 5th Workshop of the Cross-Language Evaluation Forum, CLEF 2004, Bath, UK, September 15-17, 2004, Revised Selected Papers. Lecture Notes in Computer Science, vol. 3491, Springer, pp. 446-457. https://doi.org/10.1007/11519645_44

Cross-Lingual Question Answering Using Off-the-Shelf Machine Translation. / Ahn, Kisuh; Alex, Beatrice; Bos, Johan et al.
Multilingual Information Access for Text, Speech and Images: 5th Workshop of the Cross-Language Evaluation Forum, CLEF 2004, Bath, UK, September 15-17, 2004, Revised Selected Papers. Springer, 2005. p. 446-457 (Lecture Notes in Computer Science; Vol. 3491).

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

TY - GEN

T1 - Cross-Lingual Question Answering Using Off-the-Shelf Machine Translation

AU - Ahn, Kisuh

AU - Alex, Beatrice

AU - Bos, Johan

AU - Dalmas, Tiphaine

AU - Leidner, Jochen L.

AU - Smillie, Matthew B.

PY - 2005

Y1 - 2005

N2 - We show how to adapt an existing monolingual open-domain QA system to perform in a cross-lingual environment, using off-the-shelf machine translation software. In our experiments we use French and German as source language, and English as target language. For answering factoid questions, our system performs with an accuracy of 16% (German to English) and 20% (French to English), respectively. The loss of correctly answered questions caused by the MT component is estimated at 10% for French, and 15% for German. The accuracy of our system on correctly translated questions is 28% for German and 29% for French.

AB - We show how to adapt an existing monolingual open-domain QA system to perform in a cross-lingual environment, using off-the-shelf machine translation software. In our experiments we use French and German as source language, and English as target language. For answering factoid questions, our system performs with an accuracy of 16% (German to English) and 20% (French to English), respectively. The loss of correctly answered questions caused by the MT component is estimated at 10% for French, and 15% for German. The accuracy of our system on correctly translated questions is 28% for German and 29% for French.

U2 - 10.1007/11519645_44

DO - 10.1007/11519645_44

M3 - Conference contribution

SN - 978-3-540-27420-9

T3 - Lecture Notes in Computer Science

SP - 446

EP - 457

BT - Multilingual Information Access for Text, Speech and Images

PB - Springer

ER -

Ahn K, Alex B, Bos J, Dalmas T, Leidner JL, Smillie MB. Cross-Lingual Question Answering Using Off-the-Shelf Machine Translation. In Multilingual Information Access for Text, Speech and Images: 5th Workshop of the Cross-Language Evaluation Forum, CLEF 2004, Bath, UK, September 15-17, 2004, Revised Selected Papers. Springer. 2005. p. 446-457. (Lecture Notes in Computer Science). doi: 10.1007/11519645_44

Cross-Lingual Question Answering Using Off-the-Shelf Machine Translation

Abstract / Description of output

Publication series

Access to Document

Fingerprint

Projects

Stanford Strategic Alliance

Cite this