Team Flow at DRC2022: Pipeline System for Travel Destination Recommendation Task in Spoken Dialogue
This is an incremental system for a specific competition task, addressing travel recommendation in spoken dialogue.
The team built a pipeline dialogue system for a travel recommendation competition, using GPT-2 for NLU and NLG and rule-based DST and policy, but found that limited training data and policy issues led to poor performance.
To improve the interactive capabilities of a dialogue system, e.g., to adapt to different customers, the Dialogue Robot Competition (DRC2022) was held. As one of the teams, we built a dialogue system with a pipeline structure containing four modules. The natural language understanding (NLU) and natural language generation (NLG) modules were GPT-2 based models, and the dialogue state tracking (DST) and policy modules were designed on the basis of hand-crafted rules. After the preliminary round of the competition, we found that the low variation in training examples for the NLU and failed recommendation due to the policy used were probably the main reasons for the limited performance of the system.