Previous studies mostly use a fine-tuned Language Model (LM) to strengthen the constraints but ignore the fact that the potential of diversity could improve the effectiveness of generated data.
To address these issues, we propose the Adversarial Mixing Policy (AMP), organized in a min-max-rand formulation, to relax the Locally Linear Constraints in Mixup.
Emotion Recognition in Conversations (ERC) is essential for building empathetic human-machine systems.
Ranked #7 on Emotion Recognition in Conversation on IEMOCAP
Task 1 of the DSTC8-track1 challenge aims to develop an end-to-end multi-domain dialogue system to accomplish complex users' goals under tourist information desk settings.