Search Results for author: Pierre-Emmanuel Mazaré

Found 7 papers, 6 papers with code

Data Augmenting Contrastive Learning of Speech Representations in the Time Domain

1 code implementation2 Jul 2020 Eugene Kharitonov, Morgane Rivière, Gabriel Synnaeve, Lior Wolf, Pierre-Emmanuel Mazaré, Matthijs Douze, Emmanuel Dupoux

Contrastive Predictive Coding (CPC), based on predicting future segments of speech based on past segments is emerging as a powerful algorithm for representation learning of speech signal.

Contrastive Learning Data Augmentation +1

Unsupervised pretraining transfers well across languages

2 code implementations7 Feb 2020 Morgane Rivière, Armand Joulin, Pierre-Emmanuel Mazaré, Emmanuel Dupoux

Cross-lingual and multi-lingual training of Automatic Speech Recognition (ASR) has been extensively investigated in the supervised setting.

Automatic Speech Recognition

Libri-Light: A Benchmark for ASR with Limited or No Supervision

1 code implementation17 Dec 2019 Jacob Kahn, Morgane Rivière, Weiyi Zheng, Evgeny Kharitonov, Qiantong Xu, Pierre-Emmanuel Mazaré, Julien Karadayi, Vitaliy Liptchinsky, Ronan Collobert, Christian Fuegen, Tatiana Likhomanenko, Gabriel Synnaeve, Armand Joulin, Abdel-rahman Mohamed, Emmanuel Dupoux

Additionally, we provide baseline systems and evaluation metrics working under three settings: (1) the zero resource/unsupervised setting (ABX), (2) the semi-supervised setting (PER, CER) and (3) the distant supervision setting (WER).

 Ranked #1 on Speech Recognition on Libri-Light test-other (ABX-across metric)

Speech Recognition

Reference-less Quality Estimation of Text Simplification Systems

1 code implementation WS 2018 Louis Martin, Samuel Humeau, Pierre-Emmanuel Mazaré, Antoine Bordes, Éric Villemonte de la Clergerie, Benoît Sagot

We show that n-gram-based MT metrics such as BLEU and METEOR correlate the most with human judgment of grammaticality and meaning preservation, whereas simplicity is best evaluated by basic length-based metrics.

Machine Translation Text Simplification +1

Training Millions of Personalized Dialogue Agents

1 code implementation EMNLP 2018 Pierre-Emmanuel Mazaré, Samuel Humeau, Martin Raison, Antoine Bordes

Current dialogue systems are not very engaging for users, especially when trained end-to-end without relying on proactive reengaging scripted strategies.

Weaver: Deep Co-Encoding of Questions and Documents for Machine Reading

no code implementations27 Apr 2018 Martin Raison, Pierre-Emmanuel Mazaré, Rajarshi Das, Antoine Bordes

This paper aims at improving how machines can answer questions directly from text, with the focus of having models that can answer correctly multiple types of questions and from various types of texts, documents or even from large collections of them.

Open-Domain Question Answering Reading Comprehension

Cannot find the paper you are looking for? You can Submit a new open access paper.