---
abstract: |-
This paper presents a novel strategy for translating lists
of keyphrases. Typical keyphrase lists appear in
scientific articles, information retrieval systems and
web page meta-data. Our system combines a statistical
translation model trained on a bilingual corpus of
scientific papers with sense-focused look-up in a large
bilingual terminological resource. For the latter,
we developed a novel technique that benefits from viewing
the keyphrase list as contextual help for sense
disambiguation. The optimal combination of modules was
discovered by a genetic algorithm. Our work applies to
the French / English language pair.
altloc: []
chapter: ~
commentary: ~
commref: ~
confdates: Septembre 19-26
conference: 'Recent Advances in Natural Language Processing, Machine Translation Workshop'
confloc: 'Borovets, Bulgaria'
contact_email: ~
creators_id:
- pythonner
- ''
- ''
creators_name:
- family: Nadeau
given: David
honourific: ''
lineage: ''
- family: Barrière
given: Caroline
honourific: ''
lineage: ''
- family: George
given: Foster
honourific: ''
lineage: ''
date: 2005
date_type: published
datestamp: 2005-11-12
department: ~
dir: disk0/00/00/46/03
edit_lock_since: ~
edit_lock_until: ~
edit_lock_user: ~
editors_id: []
editors_name:
- family: Hahn
given: Walther V.
honourific: ''
lineage: ''
- family: Hutchins
given: John
honourific: ''
lineage: ''
- family: Vertan
given: Cristina
honourific: ''
lineage: ''
eprint_status: archive
eprintid: 4603
fileinfo: /style/images/fileicons/application_pdf.png;/4603/1/NRC%2D48286.pdf
full_text_status: public
importid: ~
institution: ~
isbn: ~
ispublished: pub
issn: ~
item_issues_comment: []
item_issues_count: 0
item_issues_description: []
item_issues_id: []
item_issues_reported_by: []
item_issues_resolved_by: []
item_issues_status: []
item_issues_timestamp: []
item_issues_type: []
keywords: 'statistical machine translation, lexical resources, keyphrase list.'
lastmod: 2011-03-11 08:56:13
latitude: ~
longitude: ~
metadata_visibility: show
note: ~
number: ~
pagerange: 36-41
pubdom: FALSE
publication: ~
publisher: ~
refereed: TRUE
referencetext: |-
Peter F. Brown, Stephen A. Della Pietra, Vincent J. Della Pietra, and Robert L. Mercer (1993). The Mathematics of Machine Translation: Parameter Estimation. Computational Linguistics 19(2), 1993.
Yunbo Cao and Hang Li (2002). Base Noun Phrase Translation Using Web Data and the EM Algorithm. Coling02.
Nigel Collier, Hideki Hirakawa, and Akira Kumano (1998). Machine Translation vs. Dictionary Term Translation - a Comparison for English-Japanese News Article Alignment. ColingACL98.
P. Fung and K. McKeown (1997). A Technical Wordand Term-Translation Aid Using Noisy Parallel Corpora across Language Groups. Machine Translation.
Philipp Koehn and Kevin Knight (2003). Feature-Rich Statistical Translation of Noun Phrases. ACL03.
Philipp Koehn, Franz Josef Och, and Daniel Marcu (2003). Statistical Phrase-Based Translation. NAACL03.
Julian Kupiec (1993). An Algorithm For Finding Noun Phrase Correspondences In Bilingual Corpora. ACL93.
Robert C. Moore (2003). Learning Translations of Named Entity Phrases from Parallel Corpora. EACL03.
Fatiha Sadat, Akira Maeda, Masatoshi Yoshikawa, and Shunsuke Uemura 2001. Query Expansion Techniques for the CLEF Bilingual Track. In Proceedings of the CLEF 2001 Workshop on Cross-language System Evaluation Campaign, pp. 99-104, Darmstadt, Germany.
Nizar Hibash and Bonnie Dorr (2002). Handling Translation Divergences: Combining Statistical and Symbolic Techniques in Generation-Heavy Machine Translation. AMT02.
Judith Klavans and Philipp Resnik (1994). The Balancing Act: Combining Symbolic and Statistical Approaches to Language. ACL Workshop Proceedings.
David Nadeau, Mario Jarmasz, Caroline Barrière, George Foster and Claude St-Jacques (2004). Using COTS Search Engines and Custom Query Strategies at CLEF. Cross-Language Evaluation Forum CLEF 2004.
relation_type: []
relation_uri: []
reportno: ~
rev_number: 12
series: ~
source: ~
status_changed: 2007-09-12 17:01:10
subjects:
- comp-sci-lang
succeeds: ~
suggestions: ~
sword_depositor: ~
sword_slug: ~
thesistype: ~
title: 'BIKE: Bilingual Keyphrase Experiments'
type: confpaper
userid: 5664
volume: ~