Puhai Yang — accepted AI-conference papers

2024

Rethinking Task-Oriented Dialogue Systems: From Complex Modularity to Zero-Shot Autonomous Agent

Heng-Da Xu, Xian-Ling Mao, Puhai Yang, Fanshu Sun, Heyan Huang

ACL 2024long

Task-oriented dialogue (TOD) systems are predominantly designed to be composed of several functional modules (e.g. dialogue state tracker, dialogue policy, natural language generation) whether they are pipeline or end-to-end architectures. However, this modular design not only heavily relies on mass…

Cited by 12 Source ↗PDF ↗code ↗Scholar ↗

2021

Comprehensive Study: How the Context Information of Different Granularity Affects Dialogue State Tracking?

Puhai Yang, Heyan Huang, Xian-Ling Mao

ACL 2021long

Dialogue state tracking (DST) plays a key role in task-oriented dialogue systems to monitor the user’s goal. In general, there are two strategies to track a dialogue state: predicting it from scratch and updating it from previous state. The scratch-based strategy obtains each slot value by inquiring…

Cited by 13 Source ↗PDF ↗code ↗Scholar ↗