Nicolas Usunier

Multi-class to Binary reduction of Large-scale classification Problems

2015 · HAL (Le Centre pour la Communication Scientifique Directe)

International audience

Improving Neural Language Models with a Continuous Cache

2016 · arXiv (Cornell University)

We propose an extension to neural network language models to adapt their prediction to the recent history. Our model is a simplified version of memory augmented networks, which stores past hidden activations as memory and …

Fully Convolutional Speech Recognition

2018 · arXiv (Cornell University)

Current state-of-the-art speech recognition systems build on recurrent neural networks for acoustic and/or language modeling, and rely on feature extraction pipelines to extract mel-filterbanks or cepstral coefficients. In this paper we present an alternative approach …

Large-scale Simple Question Answering with Memory Networks

2015 · arXiv (Cornell University)

Training large-scale question answering systems is complicated because training sources usually cover a small portion of the range of possible questions. This paper studies the impact of multitask and transfer learning for simple question answering; …