Joint Space Neural Probabilistic Language Model for Statistical Machine Translation

TL;DR

This paper introduces a joint space neural probabilistic language model for statistical machine translation, leveraging non-parametric Bayesian methods to improve translation quality, especially with limited training data.

Contribution

It proposes a novel joint space ngram-HMM neural language model using non-parametric Bayesian construction for SMT applications.

Findings

Noise treatment improved BLEU score by 0.20 points

Model performs well with small training corpora

System combination enhances translation quality

Abstract

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.