research
∙
04/03/2022
Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generation
Current language generation models suffer from issues such as repetition...
share
research
∙
02/09/2021
SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks
Graph neural networks (GNNs) work well when the graph structure is provi...
research
∙
10/15/2020
Diverse Keyphrase Generation with Neural Unlikelihood Training
In this paper, we study sequence-to-sequence (S2S) keyphrase generation ...
research
∙
06/21/2019
A Study of State Aliasing in Structured Prediction with RNNs
End-to-end reinforcement learning agents learn a state representation an...
research
∙
12/17/2018
From FiLM to Video: Multi-turn Question Answering with Multi-modal Context
Understanding audio-visual content and the ability to have an informativ...
research
∙
12/03/2018
Towards Solving Text-based Games by Producing Adaptive Action Spaces
To solve a text-based game, an agent needs to formulate valid text comma...
research
∙
11/24/2018
Keep Drawing It: Iterative language-based image generation and editing
Conditional text-to-image generation approaches commonly focus on genera...
research
∙
06/29/2018
TextWorld: A Learning Environment for Text-based Games
We introduce TextWorld, a sandbox learning environment for the training ...
research
∙
12/19/2017
Safe Policy Improvement with Baseline Bootstrapping
A common goal in Reinforcement Learning is to derive a good strategy giv...
research
∙
06/29/2017
Relevance of Unsupervised Metrics in Task-Oriented Dialogue for Evaluating Natural Language Generation
Automated metrics such as BLEU are widely used in the machine translatio...
research
∙
06/06/2017
A Frame Tracking Model for Memory-Enhanced Dialogue Systems
Recently, resources and tasks were proposed to go beyond state tracking ...
research
∙
03/31/2017
Frames: A Corpus for Adding Memory to Goal-Oriented Dialogue Systems
This paper presents the Frames dataset (Frames is available at http://da...
research
∙
06/30/2016
A Sequence-to-Sequence Model for User Simulation in Spoken Dialogue Systems
User simulation is essential for generating enough data to train a stati...
research
∙
06/10/2016