Deriving a Bilingual Lexicon for Cross-Language Information Retrieval

Djoerd Hiemstra

Deriving a Bilingual Lexicon for Cross-Language Information Retrieval

Djoerd Hiemstra

Databases (Former)

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

31 Downloads (Pure)

Abstract

In this paper we describe a systematic approach to derive a bilingual lexicon automatically from parallel corpora. Following this approach, a lexicon was derived from the English and Dutch version of the Agenda 21 corpus. With the lexicon and a part of the corpus that was not used to derive the lexicon, a bilingual retrieval environment was build. Recall and precision of monolingual (Dutch) retrieval was compared to recall and precision of bilingual (Dutch-to-English) retrieval. An experiment was conducted with the help of eight naive users who formulated queries and judged the relevance of retrieved fragments. The experiment shows 78% precision and 51% relative recall of monolingual retrieval, against 67% precision and 82% relative recall of bilingual retrieval.

Original language	English
Title of host publication	GRONICS '97
Subtitle of host publication	Proceedings of the Fourth Groningen International Information Technology Conference for Students
Editors	M. Heemskerk, M. Diepenhorst
Place of Publication	Groningen
Publisher	University of Groningen
Pages	21-26
Number of pages	6
ISBN (Print)	9789036707299
Publication status	Published - 1997
Event	Fourth Groningen International Information Technology Conference for Students, GRONICS 1997 - Groningen, Netherlands Duration: 21 Feb 1997 → 21 Feb 1997 Conference number: 4

Conference

Conference	Fourth Groningen International Information Technology Conference for Students, GRONICS 1997
Abbreviated title	GRONICS
Country/Territory	Netherlands
City	Groningen
Period	21/02/97 → 21/02/97

Keywords

EWI-9494
IR-66999
METIS-122303
Lexical acquisition
Parallel corpora
Statistical Natural Language Processing
Cross Language Information Retrieval

Access to Document

Hiemstra97derivingFinal published version, 140 KB

Cite this

@inproceedings{3aaaa3bdf8924f289ca41a75d801f2b0,

title = "Deriving a Bilingual Lexicon for Cross-Language Information Retrieval",

abstract = "In this paper we describe a systematic approach to derive a bilingual lexicon automatically from parallel corpora. Following this approach, a lexicon was derived from the English and Dutch version of the Agenda 21 corpus. With the lexicon and a part of the corpus that was not used to derive the lexicon, a bilingual retrieval environment was build. Recall and precision of monolingual (Dutch) retrieval was compared to recall and precision of bilingual (Dutch-to-English) retrieval. An experiment was conducted with the help of eight naive users who formulated queries and judged the relevance of retrieved fragments. The experiment shows 78% precision and 51% relative recall of monolingual retrieval, against 67% precision and 82% relative recall of bilingual retrieval.",

keywords = "EWI-9494, IR-66999, METIS-122303, Lexical acquisition, Parallel corpora, Statistical Natural Language Processing, Cross Language Information Retrieval",

author = "Djoerd Hiemstra",

year = "1997",

language = "English",

isbn = "9789036707299",

pages = "21--26",

editor = "M. Heemskerk and M. Diepenhorst",

booktitle = "GRONICS '97",

publisher = "University of Groningen",

note = "Fourth Groningen International Information Technology Conference for Students, GRONICS 1997, GRONICS ; Conference date: 21-02-1997 Through 21-02-1997",

}

Hiemstra, D 1997, Deriving a Bilingual Lexicon for Cross-Language Information Retrieval. in M Heemskerk & M Diepenhorst (eds), GRONICS '97: Proceedings of the Fourth Groningen International Information Technology Conference for Students. University of Groningen, Groningen, pp. 21-26, Fourth Groningen International Information Technology Conference for Students, GRONICS 1997, Groningen, Netherlands, 21/02/97.

Deriving a Bilingual Lexicon for Cross-Language Information Retrieval. / Hiemstra, Djoerd.
GRONICS '97: Proceedings of the Fourth Groningen International Information Technology Conference for Students. ed. / M. Heemskerk; M. Diepenhorst. Groningen: University of Groningen, 1997. p. 21-26.

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

TY - GEN

T1 - Deriving a Bilingual Lexicon for Cross-Language Information Retrieval

AU - Hiemstra, Djoerd

N1 - Conference code: 4

PY - 1997

Y1 - 1997

N2 - In this paper we describe a systematic approach to derive a bilingual lexicon automatically from parallel corpora. Following this approach, a lexicon was derived from the English and Dutch version of the Agenda 21 corpus. With the lexicon and a part of the corpus that was not used to derive the lexicon, a bilingual retrieval environment was build. Recall and precision of monolingual (Dutch) retrieval was compared to recall and precision of bilingual (Dutch-to-English) retrieval. An experiment was conducted with the help of eight naive users who formulated queries and judged the relevance of retrieved fragments. The experiment shows 78% precision and 51% relative recall of monolingual retrieval, against 67% precision and 82% relative recall of bilingual retrieval.

AB - In this paper we describe a systematic approach to derive a bilingual lexicon automatically from parallel corpora. Following this approach, a lexicon was derived from the English and Dutch version of the Agenda 21 corpus. With the lexicon and a part of the corpus that was not used to derive the lexicon, a bilingual retrieval environment was build. Recall and precision of monolingual (Dutch) retrieval was compared to recall and precision of bilingual (Dutch-to-English) retrieval. An experiment was conducted with the help of eight naive users who formulated queries and judged the relevance of retrieved fragments. The experiment shows 78% precision and 51% relative recall of monolingual retrieval, against 67% precision and 82% relative recall of bilingual retrieval.

KW - EWI-9494

KW - IR-66999

KW - METIS-122303

KW - Lexical acquisition

KW - Parallel corpora

KW - Statistical Natural Language Processing

KW - Cross Language Information Retrieval

M3 - Conference contribution

SN - 9789036707299

SP - 21

EP - 26

BT - GRONICS '97

A2 - Heemskerk, M.

A2 - Diepenhorst, M.

PB - University of Groningen

CY - Groningen

T2 - Fourth Groningen International Information Technology Conference for Students, GRONICS 1997

Y2 - 21 February 1997 through 21 February 1997

ER -

Deriving a Bilingual Lexicon for Cross-Language Information Retrieval

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this