Abstract
Current Statistical Machine Translation (SMT) systems translate texts sentence by sentence without considering any cross-sentential context. Assuming independence between sentences makes it difficult to take certain translation decisions when the necessary information cannot be determined locally. We argue for the necessity to include cross-sentence dependencies in SMT. As a case in point, we study the problem of pronominal anaphora translation by manually evaluating German-English SMT output. We then present a word dependency model for SMT, which can represent links between word pairs in the same or in different sentences. We use this model to integrate the output of a coreference resolution system into English-German SMT with a view to improving the translation of anaphoric pronouns.
| Original language | English |
|---|---|
| Title of host publication | 7th International Workshop on Spoken Language Translation, Paris, France, 2/12/10 |
| Publication date | 3 Dec 2010 |
| Publication status | Published - 3 Dec 2010 |
| Externally published | Yes |