Publication at Faculty of Mathematics and Physics |
2011
Abstract
Majority of present machine translation systems do not address the retaining of text coherency, they translate just isolated sentences. On the other hand, the authors of anaphora resolvers rarely integrate these tools into more complex scenarios, e.g. the task of machine translation.
We propose the ways how machine translation systems can utilize the knowledge of anaphoric relations both in the source as well as in the target language in order to improve the quality of translation. Specifically, we present how to incorporate anaphora resolution into the process of English to Czech translation using the TectoMT system.