External Knowledge Selection with Weighted Negative Sampling in Knowledge-grounded Task-oriented Dialogue Systems
This work addresses the problem of improving knowledge selection and response generation in spoken task-oriented dialogue systems, but it is incremental as it builds on existing benchmarks and methods.
The paper tackled the challenge of building a task-oriented dialogue system using external knowledge on spoken conversations, achieving a ranking of 7th out of 16 teams in objective evaluation and 6th in human evaluation.
Constructing a robust dialogue system on spoken conversations bring more challenge than written conversation. In this respect, DSTC10-Track2-Task2 is proposed, which aims to build a task-oriented dialogue (TOD) system incorporating unstructured external knowledge on a spoken conversation, extending DSTC9-Track1. This paper introduces our system containing four advanced methods: data construction, weighted negative sampling, post-training, and style transfer. We first automatically construct a large training data because DSTC10-Track2 does not release the official training set. For the knowledge selection task, we propose weighted negative sampling to train the model more fine-grained manner. We also employ post-training and style transfer for the response generation task to generate an appropriate response with a similar style to the target response. In the experiment, we investigate the effect of weighted negative sampling, post-training, and style transfer. Our model ranked 7 out of 16 teams in the objective evaluation and 6 in human evaluation.