Using a target language model for domain independent lexical disambiguation

Jim Cowie, Yevgeny Ludovik, Sergei Nirenburg


Abstract
In this paper we describe a lexical disambiguation algorithm based on a statistical language model we call maximum likelihood disambiguation. The maximum likelihood method depends solely on the target language. The model was trained on a corpus of American English newspaper texts. Its performance was tested using output from a transfer based translation system between Turkish and English. The method is source language independent, and can be used for systems translating from any language into English.
Anthology ID:
1999.mtsummit-1.61
Volume:
Proceedings of Machine Translation Summit VII
Month:
September 13-17
Year:
1999
Address:
Singapore, Singapore
Venue:
MTSummit
SIG:
Publisher:
Note:
Pages:
417–420
Language:
URL:
https://aclanthology.org/1999.mtsummit-1.61
DOI:
Bibkey:
Cite (ACL):
Jim Cowie, Yevgeny Ludovik, and Sergei Nirenburg. 1999. Using a target language model for domain independent lexical disambiguation. In Proceedings of Machine Translation Summit VII, pages 417–420, Singapore, Singapore.
Cite (Informal):
Using a target language model for domain independent lexical disambiguation (Cowie et al., MTSummit 1999)
Copy Citation:
PDF:
https://aclanthology.org/1999.mtsummit-1.61.pdf