Exploring Pair-Wise NMT for Indian Languages
arXiv:2012.05786
Abstract
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.
arXiv commentICON 2020 Short paper
References in corpus (6)
- Decoupled Weight Decay Regularization
- PMIndia -- A Collection of Parallel Corpora of Languages of India
- Multilingual NMT with a language-independent attention bridge
- Neural machine translation for low-resource languages
- A Multilingual Parallel Corpora Collection Effort for Indian Languages
- A Baseline Neural Machine Translation System for Indian Languages