We propose several techniques for improving statistical machine translation between closely-related languages with scarce resources. We use character-level translation trained on ...
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...
In this paper we compare and contrast two approaches to Machine Translation (MT): the CMU-UKA Syntax Augmented Machine Translation system (SAMT) and UPC-TALP N-gram-based Statisti...
Randomised techniques allow very big language models to be represented succinctly. However, being batch-based they are unsuitable for modelling an unbounded stream of language whi...