Title |
Identifying bilingual Multi-Word Expressions for Statistical Machine Translation |
Authors |
Dhouha Bouamor, Nasredine Semmar and Pierre Zweigenbaum |
Abstract |
MultiWord Expressions (MWEs) repesent a key issue for numerous applications in Natural Language Processing (NLP) especially for Machine Translation (MT). In this paper, we describe a strategy for detecting translation pairs of MWEs in a French-English parallel corpus. In addition we introduce three methods aiming to integrate extracted bilingual MWE S in M OSES, a phrase based Statistical Machine Translation (SMT) system. We experimentally show that these textual units can improve translation quality. |
Topics |
MultiWord Expressions & Collocations, Machine Translation, SpeechToSpeech Translation, Multilinguality |
Full paper |
Identifying bilingual Multi-Word Expressions for Statistical Machine Translation |
Bibtex |
@InProceedings{BOUAMOR12.886,
author = {Dhouha Bouamor and Nasredine Semmar and Pierre Zweigenbaum}, title = {Identifying bilingual Multi-Word Expressions for Statistical Machine Translation}, booktitle = {Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC'12)}, year = {2012}, month = {may}, date = {23-25}, address = {Istanbul, Turkey}, editor = {Nicoletta Calzolari (Conference Chair) and Khalid Choukri and Thierry Declerck and Mehmet Uğur Doğan and Bente Maegaard and Joseph Mariani and Asuncion Moreno and Jan Odijk and Stelios Piperidis}, publisher = {European Language Resources Association (ELRA)}, isbn = {978-2-9517408-7-7}, language = {english} } |