kimdanny/user-simulation-t5
Official Code for SIGIR 2022 "A Multi-task Based Neural Model to Simulate Users in Goal Oriented Dialogue Systems". User Simulator generates user-side utterance, predicts user's next action and satisfaction level.
This project helps evaluate and improve goal-oriented dialogue systems, such as chatbots or virtual assistants, by simulating how a real user would interact. It takes the current dialogue state and system response as input and outputs what the user would say next, their likely action, and their overall satisfaction level. This is for researchers and developers building and testing conversational AI systems.
No commits in the last 6 months.
Use this if you need to realistically simulate user behavior to test, benchmark, or train your goal-oriented dialogue system without needing actual human users.
Not ideal if you are looking for a general-purpose natural language generation model or a tool for open-ended conversation.
Stars
37
Forks
1
Language
Python
License
—
Category
Last pushed
Jul 14, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/kimdanny/user-simulation-t5"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
gunthercox/chatterbot-corpus
A multilingual dialog corpus
EdinburghNLP/awesome-hallucination-detection
List of papers on hallucination detection in LLMs.
jfainberg/self_dialogue_corpus
The Self-dialogue Corpus - a collection of self-dialogues across music, movies and sports
jkkummerfeld/irc-disentanglement
Dataset and model for disentangling chat on IRC
Tomiinek/MultiWOZ_Evaluation
Unified MultiWOZ evaluation scripts for the context-to-response task.