Papers by Puhai Yang
Comprehensive Study: How the Context Information of Different Granularity Affects Dialogue State Tracking? (2021.acl-long)
Copied to clipboard
| Challenge: | Dialogue state tracking (DST) plays a key role in task-oriented dialogue systems to monitor the user’s goal. |
| Approach: | They propose to use scratch-based and previous-based strategies to track dialogue state . they explore how different granularities affect dialogue state tracking . |
| Outcome: | The scratch-based strategy obtains each slot value by inquiring all the dialogue history, while the previous-based method is not very useful for long-dependency dialogue state tracking. |
Rethinking Task-Oriented Dialogue Systems: From Complex Modularity to Zero-Shot Autonomous Agent (2024.acl-long)
Copied to clipboard
| Challenge: | Task-oriented dialogue systems are designed to be composed of several functional modules, but lacks a general-purpose instruction-following language model. |
| Approach: | They propose a fully zero-shot autonomous TOD agent that leverages a general-purpose instruction-following language model to decide what to do at each dialogue turn. |
| Outcome: | The proposed agent can perform tasks in real-life scenarios with a general-purpose instruction-following language model. |