Symbolic Dialogue for General Domain State Tracking
ID:84
Submission ID:168 View Protection:ATTENDEE
Updated Time:2024-08-20 11:15:13 Hits:12
Oral Presentation
Abstract
Task-oriented dialogue (TOD) is a system that helps users achieve their goals. While the task is reviewed and improved regularly, a formal system for industrial standards has not yet been established. Dialogue state tracking is a sub-task that involves predicting current dialogue slot values given the conversation and in some cases, the slots that are being required or informed. Based on a well-documented schema with instructions for possible slots and intents along with their descriptions, schema-guided TOD exploits a concrete set of guidelines to add extra context and perform general zero-shot ability on state tracking. Despite having contextual schema descriptions, language models hardly keep up with a full TOD dialogue flow. The TOD system as a whole lacks the mechanics to detect out-of-scope events, decide when to query the database, and is hardly extensible for further processing. To address these issues, we propose a full TOD system designed to overcome the listed weaknesses. Additionally, we experiment with dialogue state tracking, the system’s first stage, and measure out-of-scope detection effectiveness via user-undefined actions.
Keywords
task-oriented dialogue,schema-guided,symbolic reasoning,open-domain dialogue,dialogue system,schema actions
Submission Author
Hung Nguyen Quoc
FPT University
Tien Nguyen Van
Pythera AI
Hieu Pham Trung
Pythera AI
Trung Nguyen Quoc
FPT University
Truong Hoang Vinh
Ho Chi Minh City Open University
Tuan Le-Viet
Ho Chi Minh City Open University
Comment submit