Chia-Hsuan-Lee/DST-as-Prompting
Source code for Dialogue State Tracking with a Language Model using Schema-Driven Prompting
This project helps developers build conversational AI agents that can accurately understand and track user requests over multiple turns. It takes a structured conversation history and predefined user intents (schema) as input, then identifies and extracts key information (slot values) from the dialogue. AI researchers and conversational system developers would use this to improve their dialogue state tracking models.
No commits in the last 6 months.
Use this if you are a conversational AI developer working on an agent that needs to understand and remember user preferences across a multi-turn conversation, and you want to fine-tune a language model for this specific task.
Not ideal if you need a pre-trained, out-of-the-box solution for general natural language understanding without specific fine-tuning capabilities.
Stars
65
Forks
13
Language
Python
License
—
Category
Last pushed
Oct 26, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/Chia-Hsuan-Lee/DST-as-Prompting"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
gdufsnlp/PMAES
Code for Paper "PMAES: Prompt-mapping Contrastive Learning for Cross-prompt Automated Essay...
TUM-NLPLab-2022/PARL-A-Dialog-System-Framework-with-Prompts-as-Actions-for-Reinforcement-Learning
This is the offical repo for the paper "PARL: A Dialog System Framework with Prompts as Actions...