Exploring Pair-Wise NMT for Indian Languages
This work provides a method to improve machine translation performance for low-resource Indian languages, which could benefit users and researchers working with these specific languages.
This paper addresses the task of improving pair-wise machine translation for low-resource Indian languages. The authors demonstrate that back-translation through a filtered process and subsequent fine-tuning on limited pair-wise corpora can significantly improve multilingual NMT models, achieving state-of-the-art results for various Indian languages.
In this paper, we address the task of improving pair-wise machine translation for specific low resource Indian languages. Multilingual NMT models have demonstrated a reasonable amount of effectiveness on resource-poor languages. In this work, we show that the performance of these models can be significantly improved upon by using back-translation through a filtered back-translation process and subsequent fine-tuning on the limited pair-wise language corpora. The analysis in this paper suggests that this method can significantly improve a multilingual model's performance over its baseline, yielding state-of-the-art results for various Indian languages.