A Study of Levenshtein Transformer and Editor Transformer Models for Under-Resourced Languages

San, Mya Ei; Thu, Ye Kyaw; Hlaing, Zar Zar; Nwe, Hlaing Myat; Supnithi, Thepchai; Usanavasin, Sasiporn

doi:10.1109/isai-nlp54397.2021.9678159

Cited by 2 publications

(1 citation statement)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We can implement the EDITOR model with soft lexical constraints or hard lexical constraints or without constraints. The authors in [46] proposed the EDITOR and Levenshtein Transformer models for two-way translation of Thai–Myanmar, Thai–English, and Myanmar–English language pairs without using any lexical constraints, and they showed that the EDITOR model achieves better translation performance in English-to-Thai, Thai-to-English, and English-to-Myanmar translation pairs. Moreover, Xu and Carpuat [44] stated that EDITOR performs more effectively than the Levenshtein Transformer when utilizing the soft lexical constraints.…”

Section: Methodsmentioning

confidence: 99%

Improving neural machine translation with POS-tag features for low-resource language pairs

Hlaing

Thu

Supnithi

et al. 2022

Heliyon

Self Cite

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 99%

Improving neural machine translation with POS-tag features for low-resource language pairs

Hlaing

Thu

Supnithi

et al. 2022

Heliyon

Self Cite

View full text Add to dashboard Cite

A Study for Enhancing Low-resource Thai-Myanmar-English Neural Machine Translation

San,

Usanavasin,

Thu

et al. 2024

ACM Trans. Asian Low-Resour. Lang. Inf. Process.

View full text Add to dashboard Cite

Several methodologies have recently been proposed to enhance the performance of low-resource Neural Machine Translation (NMT). However, these techniques have yet to be explored thoroughly in low-resource Thai and Myanmar languages. Therefore, we first applied augmentation techniques such as SwitchOut and Ciphertext Based Data Augmentation (CipherDAug) to improve NMT performance in these languages. We secondly enhanced the NMT performance by fine-tuning the pre-trained Multilingual Denoising BART model (mBART), where BART denotes Bidirectional and Auto-Regressive Transformer. We implemented three NMT systems: namely, Transformer+SwitchOut, Multi-source Transformer+CipherDAug, and fine-tuned mBART in the bidirectional translations of Thai-English-Myanmar language pairs from the ASEAN-MT corpus. Experimental results showed that Multi-source Transformer+CipherDAug significantly improved BLEU, ChrF, and TER scores over the first baseline Transformer and second baseline Edit-Based Transformer (EDITOR). The model achieved notable BLEU scores: 37.9 (English-to-Thai), 42.7 (Thai-to-English), 28.9 (English-to-Myanmar), 31.2 (Myanmar-to-English), 25.3 (Thai-to-Myanmar), and 25.5 (Myanmar-to-Thai). The fine-tuned mBART model also considerably outperformed the two baselines, except for the Myanmar-to-English pair. SwitchOut improved over the second baseline in all pairs and performed similarly to the first baseline in most cases. Lastly, we performed detailed analyses verifying that the CipherDAug and mBART models potentially facilitate improving low-resource NMT performance in Thai and Myanmar languages.

show abstract

A Study of Levenshtein Transformer and Editor Transformer Models for Under-Resourced Languages

Cited by 2 publications

References 4 publications

Improving neural machine translation with POS-tag features for low-resource language pairs

Improving neural machine translation with POS-tag features for low-resource language pairs

A Study for Enhancing Low-resource Thai-Myanmar-English Neural Machine Translation

Contact Info

Product

Resources

About