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

EasyChair Preprint no. 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: french wolof parallel corpus, low-resource language, LSTM, machine translation, Natural Language Processing, 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 no. 3082},

  year = {EasyChair, 2020}}