Machine Translation Model based on Non-parallel Corpus and Semi-supervised Transductive Learning

TL;DR

This paper introduces a semi-supervised transductive learning approach that leverages non-parallel corpora to enhance machine translation systems, especially when labeled data is scarce.

Contribution

It presents a novel method combining non-parallel corpus alignment with semi-supervised learning to expand training data for statistical machine translation.

Findings

Improved translation performance using non-parallel corpora

Effective in scenarios with limited labeled data

Combines alignment and semi-supervised learning successfully

Abstract

Although the parallel corpus has an irreplaceable role in machine translation, its scale and coverage is still beyond the actual needs. Non-parallel corpus resources on the web have an inestimable potential value in machine translation and other natural language processing tasks. This article proposes a semi-supervised transductive learning method for expanding the training corpus in statistical machine translation system by extracting parallel sentences from the non-parallel corpus. This method only requires a small amount of labeled corpus and a large unlabeled corpus to build a high-performance classifier, especially for when there is short of labeled corpus. The experimental results show that by combining the non-parallel corpus alignment and the semi-supervised transductive learning method, we can more effectively use their respective strengths to improve the performance of machine translation system.