Unsupervised Discriminative Language Model Training for Machine Translation using Simulated Confusion Sets

摘要

An unsupervised discriminative training procedure is proposed for estimating a language model (LM) for machine trans-lation (MT). An English-to-English syn-chronous context-free grammar is derived from a baseline MT system to capture translation alternatives: pairs of words, phrases or other sentence fragments that potentially compete to be the translation of the same source-language fragment. Using this grammar, a set of impostor sentences is then created for each En-glish sentence to simulate confusions that would arise if the system were to process an (unavailable) input whose correct En-glish translation is that sentence. An LM is then trained to discriminate between the original sentences and the impostors. The procedure is applied to the IWSLT Chinese-to-English translation task, and promising improvements on a state-of-the- art MT system are demonstrated.