PineauJ. x 2

bookRéférences 2

Masked language modeling and the distributional hypothesis: Order word matters pre-training for little

A possible explanation for the impressive performance of masked language model (MLM) pre-training is...

PineauJ.WilliamsA.SinhaK.JiaR.HupkesD.

The bottleneck simulator: A model-based deep reinforcement learning approach

… sentiment and ZGeneric user utterance. Although we only consider dialogue acts, sentime...

SerbanI.V.SankarC.PieperM.PineauJ.

Mots-clés associés