The distortion cost function used in Mosesstyle machine translation systems has two flaws. First, it does not estimate the future cost of known required moves, thus increasing sea...
Spence Green, Michel Galley, Christopher D. Mannin...
We present a set of algorithms that enable us to translate natural language sentences by exploiting both a translation memory and a statistical-based translation model. Our result...
Abstract--This paper presents a model for machine aided human translation (MAHT) that integrates source language text and target language acoustic information to produce the text t...
Punjabi and Hindi are two closely related languages as both originated from the same origin and having lot of syntactic and semantic similarities. These similarities make direct t...
This paper explores the use of statistical machine translation (SMT) methods for tactical natural language generation. We present results on using phrase-based SMT for learning to...