Joint Space Neural Probabilistic Language Model for Statistical Machine Translation
This work addresses the problem of resource constraints in bilingual NLP for SMT practitioners, though it is incremental in nature.
The paper tackled the challenge of applying neural probabilistic language models (NPLM) to statistical machine translation (SMT) by proposing a joint space model of an ngram-HMM language model, which improved translation results by 0.20 BLEU points when trained on a small corpus of 500,000 sentence pairs.
A neural probabilistic language model (NPLM) provides an idea to achieve the better perplexity than n-gram language model and their smoothed language models. This paper investigates application area in bilingual NLP, specifically Statistical Machine Translation (SMT). We focus on the perspectives that NPLM has potential to open the possibility to complement potentially `huge' monolingual resources into the `resource-constraint' bilingual resources. We introduce an ngram-HMM language model as NPLM using the non-parametric Bayesian construction. In order to facilitate the application to various tasks, we propose the joint space model of ngram-HMM language model. We show an experiment of system combination in the area of SMT. One discovery was that our treatment of noise improved the results 0.20 BLEU points if NPLM is trained in relatively small corpus, in our case 500,000 sentence pairs, which is often the case due to the long training time of NPLM.