Novel Document Level Features for Statistical Machine Translation

Abstract

In this paper, we introduce document level features that capture necessary information to help MT system perform better word sense disambiguation in the translation process. We describe enhancements to a Maximum Entropy based translation model, utilizing long distance contextual features identified from the span of entire document and from both source and… (More)
DOI: 10.18653/v1/W15-2520

3 Figures and Tables

Topics

  • Presentations referencing similar topics