Data Inferred Multi-word Expressions for Statistical Machine Translation

Patrick Lambert, Rafael Banchs


Abstract
This paper presents a strategy for detecting and using multi-word expressions in Statistical Machine Translation. Performance of the proposed strategy is evaluated in terms of alignment quality as well as translation accuracy. Evaluations are performed by using the Verbmobil corpus. Results from translation tasks from English-to-Spanish and from Spanish-to-English are presented and discussed.
Anthology ID:
2005.mtsummit-posters.11
Volume:
Proceedings of Machine Translation Summit X: Posters
Month:
September 13-15
Year:
2005
Address:
Phuket, Thailand
Venue:
MTSummit
SIG:
Publisher:
Note:
Pages:
396–403
Language:
URL:
https://aclanthology.org/2005.mtsummit-posters.11
DOI:
Bibkey:
Cite (ACL):
Patrick Lambert and Rafael Banchs. 2005. Data Inferred Multi-word Expressions for Statistical Machine Translation. In Proceedings of Machine Translation Summit X: Posters, pages 396–403, Phuket, Thailand.
Cite (Informal):
Data Inferred Multi-word Expressions for Statistical Machine Translation (Lambert & Banchs, MTSummit 2005)
Copy Citation:
PDF:
https://aclanthology.org/2005.mtsummit-posters.11.pdf