Context based machine translation with recurrent neural network for English–Amharic translation

Abstract

Context-aware machine translation approaches improve the quality of translation by incorporating the context of the surrounding phrases in the translation of a phrase. So far, for the low-resource language pair English-Amharic, context-aware machine translation approaches have not been investigated in depth. Moreover, the current approaches for machine translation of the low-resource language pair English-Amharic usually require a large set of parallel corpus to achieve fluency. This research investigates a new approach that translates English text to Amharic text using a combination of context based machine translation (CBMT) and a recurrent neural network machine translation (RNNMT). We built a bilingual dictionary for the CBMT to use along with a target corpus. The RNNMT model is then provided with the output of the CBMT and a parallel corpus for training. The approach is evaluated using the New Testament Bible as a corpus. Our combinational approach on English–Amharic language pair yields a performance improvement over the simple neural machine translation (NMT), while no improvement is seen over CBMT for a small dataset. We have also assessed the impact of the dictionary used by CBMT on the overall performance of the approach. The result shows that the dictionary accuracy, and hence, the CBMT output is found to affect the combinational approach.