Neural Machine Translation for Low Resource Languages using Bilingual Lexicon Induced from Comparable Corpora

TL;DR

This paper presents a method to improve neural machine translation for low-resource languages by automatically extracting parallel sentences from comparable corpora using a Siamese neural network, leading to better translation quality.

Contribution

The paper introduces an end-to-end Siamese bidirectional RNN approach to extract parallel sentences from comparable corpora, enhancing translation performance for low-resource languages.

Findings

Improved BLEU scores on English-Hindi and English-Tamil translation tasks.

Effective extraction of parallel sentences from Wikipedia articles.

Enhanced translation quality using harvested datasets.

Abstract

Resources for the non-English languages are scarce and this paper addresses this problem in the context of machine translation, by automatically extracting parallel sentence pairs from the multilingual articles available on the Internet. In this paper, we have used an end-to-end Siamese bidirectional recurrent neural network to generate parallel sentences from comparable multilingual articles in Wikipedia. Subsequently, we have showed that using the harvested dataset improved BLEU scores on both NMT and phrase-based SMT systems for the low-resource language pairs: English--Hindi and English--Tamil, when compared to training exclusively on the limited bilingual corpora collected for these language pairs.