Sean Welleck

We show that the likelihood objective itself is at fault, resulting in a model that assigns too much probability to sequences containing repeats and frequent words, unlike those from the human training distribution. Expand

We propose a method which demonstrates that a model trained on Dialogue NLI can be used to improve the consistency of dialogue model, and evaluate the method with human evaluation and with automatic metrics on a suite of evaluation sets designed to measure a dialogue model's consistency. Expand

We propose a framework for training models of text generation that operate in nonmonotonic orders; the model directly learns good orders, without any additional annotation. Expand

In this work we show how all of these problems can be addressed by extending the recently introduced unlikelihood loss (Welleck et al., 2019) to these cases. Expand

In this paper, we show that the distribution induced by a decoding algorithm can contradict this intended use; instead, the decoding algorithm may return improbable, infinite-length sequences. Expand

We propose a hierarchical visual architecture that operates on a saliency map and uses a novel attention mechanism to sequentially focus on salient regions and take additional glimpses within those regions. Expand

We propose maximum likelihood guided parameter search (MGS), which samples from a distribution over update directions that is a mixture of random search around current parameters and around the maximum likelihood gradient, with each direction weighted by its improvement in the task loss. Expand

We propose a method for non-projective dependency parsing by incrementally predicting a set of edges. Expand