| Download | - View accepted manuscript: Segment Choice Models: Feature-Rich Models for Global Distortion in Statistical Machine Translation (PDF, 261 KiB)
|
|---|
| Author | Search for: Kuhn, Roland; Search for: Yuen, D.; Search for: Simard, Michel; Search for: Paul, P.; Search for: Foster, George; Search for: Joanis, Eric; Search for: Johnson, John Howard |
|---|
| Format | Text, Article |
|---|
| Conference | Human Language Technology Conference: North American Chapter of the Association for Computational Linguistics Annual Meeting (HLT/NAACL 2006), June 5, 2006, New York City, New York, USA |
|---|
| Abstract | This paper presents a new approach to distortion (phrase reordering) in phrase-based machine translation (MT). Distortion is modeled as a sequence of choices during translation. The approach yields trainable, probabilistic distortion models that are global: they assign a probability to each possible phrase reordering. These “segment choice” models (SCMs) can be trained on “segment-aligned” sentence pairs; they can be applied during decoding or rescoring. The approach yields a metric called “distortion perplexity” (“disperp”) for comparing SCMs offline on test data, analogous to perplexity for language models. A decision-tree-based SCM is tested on Chinese-to-English translation, and outperforms a baseline distortion penalty approach at the 99% confidence level. |
|---|
| Publication date | 2006 |
|---|
| In | |
|---|
| Language | English |
|---|
| NRC number | NRCC 48752 |
|---|
| NPARC number | 5763206 |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | d91d8d1e-2ad7-4710-9e57-1b902811e2a1 |
|---|
| Record created | 2009-03-29 |
|---|
| Record modified | 2020-10-09 |
|---|
