WeChat AI & ICT's Submission for DSTC9 Interactive Dialogue Evaluation Track
This work addresses dialogue system evaluation for AI assistants, showing incremental improvements in response quality and interaction.
The paper tackled knowledge-grounded and interactive dialogue tasks in DSTC9, achieving first place on human ratings and highest automated scores in sub-task 1, and third place in sub-task 2.
We participate in the DSTC9 Interactive Dialogue Evaluation Track (Gunasekara et al. 2020) sub-task 1 (Knowledge Grounded Dialogue) and sub-task 2 (Interactive Dialogue). In sub-task 1, we employ a pre-trained language model to generate topic-related responses and propose a response ensemble method for response selection. In sub-task2, we propose a novel Dialogue Planning Model (DPM) to capture conversation flow in the interaction with humans. We also design an integrated open-domain dialogue system containing pre-process, dialogue model, scoring model, and post-process, which can generate fluent, coherent, consistent, and humanlike responses. We tie 1st on human ratings and also get the highest Meteor, and Bert-score in sub-task 1, and rank 3rd on interactive human evaluation in sub-task 2.