Current language generation models suffer from issues such as repetition...
Graph neural networks (GNNs) work well when the graph structure is provi...
In this paper, we study sequence-to-sequence (S2S) keyphrase generation
...
End-to-end reinforcement learning agents learn a state representation an...
Understanding audio-visual content and the ability to have an informativ...
To solve a text-based game, an agent needs to formulate valid text comma...
Conditional text-to-image generation approaches commonly focus on genera...
We introduce TextWorld, a sandbox learning environment for the training ...
A common goal in Reinforcement Learning is to derive a good strategy giv...
Automated metrics such as BLEU are widely used in the machine translatio...
Recently, resources and tasks were proposed to go beyond state tracking ...
This paper presents the Frames dataset (Frames is available at
http://da...
User simulation is essential for generating enough data to train a
stati...
In this paper, we propose to use deep policy networks which are trained ...