Beyond Word-based Language Model in Statistical Machine Translation

TL;DR

This paper introduces a novel phrase-based language model for statistical machine translation that models phrase dependencies, addressing key issues like phrase definition, boundary detection, and data sparsity, leading to improved translation quality.

Contribution

It proposes a new phrase-based language model that effectively handles phrase definition, boundary detection, and data sparsity, enhancing translation performance.

Findings

Achieved up to +1.47 BLEU score improvement

Effectively models phrase dependencies in translation

Addresses data sparsity in phrase-based modeling

Abstract

Language model is one of the most important modules in statistical machine translation and currently the word-based language model dominants this community. However, many translation models (e.g. phrase-based models) generate the target language sentences by rendering and compositing the phrases rather than the words. Thus, it is much more reasonable to model dependency between phrases, but few research work succeed in solving this problem. In this paper, we tackle this problem by designing a novel phrase-based language model which attempts to solve three key sub-problems: 1, how to define a phrase in language model; 2, how to determine the phrase boundary in the large-scale monolingual data in order to enlarge the training set; 3, how to alleviate the data sparsity problem due to the huge vocabulary size of phrases. By carefully handling these issues, the extensive experiments on Chinese-to-English translation show that our phrase-based language model can significantly improve the translation quality by up to +1.47 absolute BLEU score.