Francis Grégoire


2018

pdf bib
Extracting Parallel Sentences with Bidirectional Recurrent Neural Networks to Improve Machine Translation
Francis Grégoire | Philippe Langlais
Proceedings of the 27th International Conference on Computational Linguistics

Parallel sentence extraction is a task addressing the data sparsity problem found in multilingual natural language processing applications. We propose a bidirectional recurrent neural network based approach to extract parallel sentences from collections of multilingual texts. Our experiments with noisy parallel corpora show that we can achieve promising results against a competitive baseline by removing the need of specific feature engineering or additional external resources. To justify the utility of our approach, we extract sentence pairs from Wikipedia articles to train machine translation systems and show significant improvements in translation performance.

2017

pdf bib
BUCC 2017 Shared Task: a First Attempt Toward a Deep Learning Framework for Identifying Parallel Sentences in Comparable Corpora
Francis Grégoire | Philippe Langlais
Proceedings of the 10th Workshop on Building and Using Comparable Corpora

This paper describes our participation in BUCC 2017 shared task: identifying parallel sentences in comparable corpora. Our goal is to leverage continuous vector representations and distributional semantics with a minimal use of external preprocessing and postprocessing tools. We report experiments that were conducted after transmitting our results.