The most advanced abstractive dialogue summarizers lack generalization
a...
Most existing approaches to Visual Question Answering (VQA) answer quest...
Previous dialogue summarization datasets mainly focus on open-domain chi...
Capturing interactions among event arguments is an essential step toward...
Existing slot filling models can only recognize pre-defined in-domain sl...
Detecting Out-of-Domain (OOD) or unknown intents from user queries is
es...
We propose a novel task, Multi-Document Driven Dialogue (MD3), in which ...
A goal-oriented visual dialogue involves multi-turn interactions between...