Leveraging Additional Resources for Improving Statistical Machine Translation on Asian Low-Resource Languages

Abstract

Phrase-based machine translation (MT) systems require large bilingual corpora for training. Nevertheless, such large bilingual corpora are unavailable for most language pairs in the world, causing a bottleneck for the development of MT. For the Asian language pairs—Japanese, Indonesian, Malay paired with Vietnamese—they are also not excluded from the case, in which there are no large bilingual corpora on these low-resource language pairs. Furthermore, although the languages are widely used in the world, there is no prior work on MT, which causes an issue for the development of MT on these languages. In this article, we conducted an empirical study of leveraging additional resources to improve MT for the Asian low-resource language pairs: translation from Japanese, Indonesian, and Malay to Vietnamese. We propose an innovative approach that lies in two strategies of building bilingual corpora from comparable data and phrase pivot translation on existing bilingual corpora of the languages paired with English. Bilingual corpora were built from Wikipedia bilingual titles to enhance bilingual data for the low-resource languages. Additionally, we introduced a combined model of the additional resources to create an effective solution to improve MT on the Asian low-resource languages. Experimental results show the effectiveness of our systems with the improvement of +2 to +7 BLEU points. This work contributes to the development of MT on low-resource languages, especially opening a promising direction for the progress of MT on the Asian language pairs.

Migration Learning and Multi-View Training for Low-Resource Machine Translation

“…This table examines the model's ability to deal with complex language structures through specific sentence examples. Among them, the Multi-Perspective Training Model has the most accurate translation quality and understanding of language structures when facing complex clause structures and culturally specific vocabulary, which proves that Multi-Perspective Training is of great help in improving such translation problems [34,35]. Fig.…”

Unsupervised Parallel Sentences of Machine Translation for Asian Language Pairs

“…this method employs multinational BERT to construct source and the destination sentence word embedding for nearest-neighbour searching, as well as self-training to adjust the models. On the BUCC 2017 bitext mining problem, we verify our strategy by recovering concurrent subsequent uses and comparing it to earlier unlabelled data [39,41].…”

Complicating the Social Networks for Better Storytelling: An Empirical Study of Chinese Historical Text and Novel

“…Data augmentation. The size of data extracted from books is usually insufficient to reach a promising number of training samples, and it may result that the deep learning-based models cannot achieve a satisfactory prediction result [36]. In this work, the speaker corpus of Records collected only 1,248 items, and a measly portion of 806 samples (64.5%) are labeled after transcribing the entire text.…”