← Search

Cyprien de Masson d'Autume

4 accepted papers

2021

Mind the Gap: Assessing Temporal Generalization in Neural Language Models

NeurIPS 2021spotlight

Our world is open-ended, non-stationary, and constantly evolving; thus what we talk about and how we talk about it change over time. This inherent dynamic nature of language contrasts with the current static language modelling paradigm, which trains and evaluates models on utterances from overlappin…

2020

A Mutual Information Maximization Perspective of Language Representation Learning

ICLR 2020spotlight

We show state-of-the-art word representation learning methods maximize an objective function that is a lower bound on the mutual information between different parts of a word sequence (i.e., a sentence). Our formulation provides an alternative perspective that unifies classical word embedding models…

Cited by 77SourceScholar
2019

Episodic Memory in Lifelong Language Learning

NeurIPS 2019poster

We introduce a lifelong language learning setup where a model needs to learn from a stream of text examples without any dataset identifier. We propose an episodic memory model that performs sparse experience replay and local adaptation to mitigate catastrophic forgetting in this setup. Experiments o…

2019

Training Language GANs from Scratch

NeurIPS 2019poster

Generative Adversarial Networks (GANs) enjoy great success at image generation, but have proven difficult to train in the domain of natural language. Challenges with gradient estimation, optimization instability, and mode collapse have lead practitioners to resort to maximum likelihood pre-training,…