thuiar/DeepUnkID

Deep Unknown Intent Detection with Margin Loss (ACL2019)

32
/ 100
Emerging

This tool helps improve conversational AI systems by identifying when a user's request doesn't match any of the chatbot's pre-programmed responses. It takes user dialogue as input and outputs a classification indicating whether the intent is known or completely new, helping developers of dialogue systems understand and respond to unexpected user queries. It is designed for anyone building or managing chatbot and virtual assistant applications.

No commits in the last 6 months.

Use this if you need to detect entirely new or unanticipated user requests that your existing conversational AI system hasn't been trained on, rather than misclassifying them as known intents.

Not ideal if you are looking for a general-purpose text classification tool that only categorizes text into predefined categories.

conversational-ai chatbot-development natural-language-understanding intent-recognition dialogue-systems
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 17 / 25

How are scores calculated?

Stars

35

Forks

11

Language

Jupyter Notebook

License

Last pushed

Dec 08, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/thuiar/DeepUnkID"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.