Context adaptation in statistical machine translation using models with exponentially decaying cache
DANLP 2010 Proceedings of the 2010 Workshop on Domain Adaptation for Natural Language Processing
| Hi-index | 0.00 |
The focus of our workshop was to use parallel corpora for machine translation. Recent experimentation has shown that the performance of SMT systems varies greatly with the source and target language. In this workshop we encouraged researchers to investigate ways to improve the performance of SMT systems for diverse languages, including morphologically more complex languages and languages with partial free word order. Prior to the workshop, in addition to soliciting relevant papers for review and possible presentation, we conducted a shared task that brought together machine translation systems for an evaluation on previously unseen data. This year's task resembled the one from last year's in many ways, but also included a manual evaluation of MT system output and focused on translation from English into other languages, whereas most other evaluations focus on translation into English. The results of the shared task were announced at the workshop, and these proceedings also include an overview paper for the shared task that summarizes the results, as well as provides information about the data used and any procedures that were followed in conducting or scoring the task. In addition, there are short papers from each participating team that describe their underlying system in some detail.