-
MLE-guided parameter search for task loss minimization in neural sequence modeling
Neural autoregressive sequence models are used to generate sequences in ...
06/04/2020 ∙ by Sean Welleck, et al. ∙
15
∙
share
read it
-
Consistency of a Recurrent Language Model With Respect to Incomplete Decoding
Despite strong performance on a variety of tasks, neural sequence models...
02/06/2020 ∙ by Sean Welleck, et al. ∙
7
∙
share
read it
-
Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training
Generative dialogue models currently suffer from a number of problems wh...
11/10/2019 ∙ by Margaret Li, et al. ∙
0
∙
share
read it
-
Neural Text Generation with Unlikelihood Training
Neural text generation is a key tool in natural language applications, b...
08/12/2019 ∙ by Sean Welleck, et al. ∙
2
∙
share
read it
-
Sequential Graph Dependency Parser
We propose a method for non-projective dependency parsing by incremental...
05/27/2019 ∙ by Sean Welleck, et al. ∙
2
∙
share
read it
-
Non-Monotonic Sequential Text Generation
Standard sequential generation methods assume a pre-specified generation...
02/05/2019 ∙ by Sean Welleck, et al. ∙
8
∙
share
read it
-
Dialogue Natural Language Inference
Consistency is a long standing issue faced by dialogue models. In this p...
11/01/2018 ∙ by Sean Welleck, et al. ∙
6
∙
share
read it
-
Loss Functions for Multiset Prediction
We study the problem of multiset prediction. The goal of multiset predic...
11/14/2017 ∙ by Sean Welleck, et al. ∙
0
∙
share
read it
-
Saliency-based Sequential Image Attention with Multiset Prediction
Humans process visual scenes selectively and sequentially using attentio...
11/14/2017 ∙ by Sean Welleck, et al. ∙
0
∙
share
read it
