Using LSTM Networks to Translate French to Senegalese Local Languages: Wolof as a Case Study

EasyChair Preprint 3082

Abstract

In this paper, we propose a neural machine translation system for Wolof, a low-resource Niger-Congo language. First we gathered a parallel corpus of 70000 aligned French-Wolof sentences. Then we developped a baseline LSTM based encoder-decoder architecture which was further extended to bidirectional LSTMs with attention mechanisms. Our models are trained on a limited amount of parallel French-Wolof data of approximately 35000 parallel sentences. Experimental results on French-Wolof translation tasks show that our approach produces promising translations in extremely low-resource conditions. The best model was able to achieve a good performance of 47% BLEU score.

Keyphrases: LSTM, Natural Language Processing, french wolof parallel corpus, low-resource language, machine translation, neural network, parallel corpus

@booklet{EasyChair:3082,
  author    = {Alla Lo and Cheikh M. Bamba Dione and Elhadji Mamadou Nguer and Sileye O. Ba and Moussa Lo},
  title     = {Using LSTM Networks to Translate French to Senegalese Local Languages: Wolof as a Case Study},
  howpublished = {EasyChair Preprint 3082},
  year      = {EasyChair, 2020}}