Download | - View final version: Improved reordering for phrase-based translation using sparse features (PDF, 347 KiB)
|
---|
Link | https://www.aclweb.org/anthology/N13-1003/ |
---|
Author | Search for: Cherry, Colin1 |
---|
Affiliation | - National Research Council of Canada. Information and Communication Technologies
|
---|
Format | Text, Article |
---|
Conference | 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL, June 9-14, 2013, Atlanta, Georgia |
---|
Abstract | There have been many recent investigations into methods to tune SMT systems using large numbers of sparse features. However, there have not been nearly so many examples of helpful sparse features, especially for phrasebased systems. We use sparse features to address reordering, which is often considered a weak point of phrase-based translation. Using a hierarchical reordering model as our baseline, we show that simple features coupling phrase orientation to frequent words or wordclusters can improve translation quality, with boosts of up to 1.2 BLEU points in Chinese-English and 1.8 in Arabic-English. We compare this solution to a more traditional maximum entropy approach, where a probability model with similar features is trained on wordaligned bitext. We show that sparse decoder features outperform maximum entropy handily, indicating that there are major advantages to optimizing reordering features directly for BLEU with the decoder in the loop. |
---|
Publication date | 2013-07-01 |
---|
Publisher | ACL |
---|
Licence | |
---|
In | |
---|
Language | English |
---|
Peer reviewed | Yes |
---|
NPARC number | 21270979 |
---|
Export citation | Export as RIS |
---|
Report a correction | Report a correction (opens in a new tab) |
---|
Record identifier | bc772d89-6cbc-4c0e-9a8d-06fe29caf286 |
---|
Record created | 2014-02-20 |
---|
Record modified | 2021-04-26 |
---|