Incremental Re-training for Post-editing SMT

OPEN ARCHIVE

Union Jack
Dannebrog

Incremental Re-training for Post-editing SMT

Show full item record

Title: Incremental Re-training for Post-editing SMT
Author: Hardt, Daniel; Elming, Jakob
Abstract: A method is presented for incremental retraining of an SMT system, in which a local phrase table is created and incrementally updated as a file is translated and post-edited. It is shown that translation data from within the same file has higher value than other domain-specific data. In two technical domains, within-file data increases BLEU score by several full points. Furthermore, a strong recency effect is documented; nearby data within the file has greater value than more distant data. It is also shown that the value of translation data is strongly correlated with a metric defined over new occurrences of ngrams. Finally, it is argued that the incremental re-training prototype could serve as the basis for a practical system which could be interactively updated in real time in a post-editing setting. Based on the results here, such an interactive system has the potential to dramatically improve translation quality.
URI: http://hdl.handle.net/10398/8272
Date: 2011-02-17
Notes: Fremlagt på The Ninth Conference of the Association for Machine Translation in the Americas 2010

Creative Commons License This work is licensed under a Creative Commons License.

Files Size Format View
Hardt_Elming.pdf 196.3Kb PDF View/Open Konferencepapir

This item appears in the following Collection(s)

Show full item record