WSD for n-best reranking and local language modeling in SMT

Abstract

We integrate semantic information at two stages of the translation process of a state-ofthe-art SMT system. A Word Sense Disambiguation (WSD) classifier produces a probability distribution over the translation candidates of source words which is exploited in two ways. First, the probabilities serve to rerank a list of n-best translations produced by the… (More)
View Slides

Topics

4 Figures and Tables

Slides referencing similar topics