Download | - View accepted manuscript: Tighter Integration of Rule-based and Statistical MT in Serial System Combination (PDF, 433 KiB)
|
---|
Author | Search for: Ueffing, Nicola; Search for: Stephan, J.; Search for: Matusov, E.; Search for: Dugast, L.; Search for: Foster, George; Search for: Kuhn, Roland; Search for: Senellart, J.; Search for: Yang, J. |
---|
Format | Text, Article |
---|
Conference | 22nd International Conference on Computational Linguistics (COLING 2008), August 18-22, 2008, Manchester, United Kingdom |
---|
Abstract | Recent papers have described machine translation (MT) based on an automatic post-editing or serial combination strategy whereby the input language is first translated into the target language by a rule-based MT (RBMT) system, then the target language output is automatically post-edited by a phrase-based statistical machine translation (SMT) system. This approach has been shown to improve MT quality over RBMT or SMT alone. In this previous work, there was a very loose coupling between the two systems: the SMT system only had access to the final 1-best translations from RBMT. Furthermore, the previous work involved European language pairs and relatively small training corpora. In this paper, we describe a more tightly integrated serial combination for the Chinese-to-English MT task. We will present experimental evaluation results on the 2008 NIST constrained data track where a significant gain in terms of both automatic and subjective metrics is achieved through the tighter coupling of the two systems. |
---|
Publication date | 2008 |
---|
In | |
---|
Language | English |
---|
NRC number | NRCC 50397 |
---|
NPARC number | 5764530 |
---|
Export citation | Export as RIS |
---|
Report a correction | Report a correction (opens in a new tab) |
---|
Record identifier | 7edabde5-a76e-4d79-ad9e-9564f39cc12d |
---|
Record created | 2009-03-29 |
---|
Record modified | 2020-08-12 |
---|