Overview of the CLEF 2004 multilingual question answering track

Bernardo Magnini; Alessandro Vallin; Christelle Ayache; Gregor Erbach; Anselmo Peñas; Maarten De Rijke; Paulo Rocha; Kiril Simov; Richard Sutcliffe

Overview of the CLEF 2004 multilingual question answering track

Bernardo Magnini, Alessandro Vallin, Christelle Ayache, Gregor Erbach, Anselmo Peñas, Maarten De Rijke, Paulo Rocha, Kiril Simov, Richard Sutcliffe

Retired Staff

Research output: Contribution to journal › Conference article › peer-review

Abstract

Following the pilot Question Answering Track at CLEF 2003, a new evaluation exercise for multilingual QA systems took place in 2004. This paper reports on the novelties introduced in the new campaign and on participants' results. Almost all the cross-language combinations between nine source languages and seven target languages were exploited to set up more than fifty different tasks, both monolingual and bilingual. New types of questions (How- questions and definition questions) were given as input to the participating systems, while just one exact answer per question was allowed as output. The evaluation exercise has highlighted some difficulties in assessing definition questions and can be improved in the future, but the overall analysis of submissions shows encouraging results.

Original language	English
Journal	CEUR Workshop Proceedings
Volume	1170
Publication status	Published - 2004
Event	2004 Cross Language Evaluation Forum Workshop, CLEF 2004, co-located with the 8th European Conference on Digital Libraries, ECDL 2004 - Bath, United Kingdom Duration: 15 Sep 2004 → 17 Sep 2004

Cite this

@article{e6563b7cd7814dd78edc5cdebe5b8dac,

title = "Overview of the CLEF 2004 multilingual question answering track",

abstract = "Following the pilot Question Answering Track at CLEF 2003, a new evaluation exercise for multilingual QA systems took place in 2004. This paper reports on the novelties introduced in the new campaign and on participants' results. Almost all the cross-language combinations between nine source languages and seven target languages were exploited to set up more than fifty different tasks, both monolingual and bilingual. New types of questions (How- questions and definition questions) were given as input to the participating systems, while just one exact answer per question was allowed as output. The evaluation exercise has highlighted some difficulties in assessing definition questions and can be improved in the future, but the overall analysis of submissions shows encouraging results.",

author = "Bernardo Magnini and Alessandro Vallin and Christelle Ayache and Gregor Erbach and Anselmo Pe{\~n}as and {De Rijke}, Maarten and Paulo Rocha and Kiril Simov and Richard Sutcliffe",

year = "2004",

language = "English",

volume = "1170",

journal = "CEUR Workshop Proceedings",

issn = "1613-0073",

note = "2004 Cross Language Evaluation Forum Workshop, CLEF 2004, co-located with the 8th European Conference on Digital Libraries, ECDL 2004 ; Conference date: 15-09-2004 Through 17-09-2004",

}

TY - JOUR

T1 - Overview of the CLEF 2004 multilingual question answering track

AU - Magnini, Bernardo

AU - Vallin, Alessandro

AU - Ayache, Christelle

AU - Erbach, Gregor

AU - Peñas, Anselmo

AU - De Rijke, Maarten

AU - Rocha, Paulo

AU - Simov, Kiril

AU - Sutcliffe, Richard

PY - 2004

Y1 - 2004

N2 - Following the pilot Question Answering Track at CLEF 2003, a new evaluation exercise for multilingual QA systems took place in 2004. This paper reports on the novelties introduced in the new campaign and on participants' results. Almost all the cross-language combinations between nine source languages and seven target languages were exploited to set up more than fifty different tasks, both monolingual and bilingual. New types of questions (How- questions and definition questions) were given as input to the participating systems, while just one exact answer per question was allowed as output. The evaluation exercise has highlighted some difficulties in assessing definition questions and can be improved in the future, but the overall analysis of submissions shows encouraging results.

AB - Following the pilot Question Answering Track at CLEF 2003, a new evaluation exercise for multilingual QA systems took place in 2004. This paper reports on the novelties introduced in the new campaign and on participants' results. Almost all the cross-language combinations between nine source languages and seven target languages were exploited to set up more than fifty different tasks, both monolingual and bilingual. New types of questions (How- questions and definition questions) were given as input to the participating systems, while just one exact answer per question was allowed as output. The evaluation exercise has highlighted some difficulties in assessing definition questions and can be improved in the future, but the overall analysis of submissions shows encouraging results.

UR - http://www.scopus.com/inward/record.url?scp=84961371175&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:84961371175

SN - 1613-0073

VL - 1170

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

T2 - 2004 Cross Language Evaluation Forum Workshop, CLEF 2004, co-located with the 8th European Conference on Digital Libraries, ECDL 2004

Y2 - 15 September 2004 through 17 September 2004

ER -

Overview of the CLEF 2004 multilingual question answering track

Abstract

Other files and links

Fingerprint

Cite this