asappresearch/dialog-intent-induction

Code and data for paper "Dialog Intent Induction with Deep Multi-View Clustering", Hugh Perkins and Yi Yang, 2019, EMNLP 2019

43
/ 100
Emerging

This project helps customer service managers automatically find new, complex customer service issues directly from conversation transcripts. It takes raw dialog data, like customer support chats or call transcripts, and groups similar conversations together based on both the customer's initial query and the support team's resolution path. The output is a set of identified 'intents' or problem types that are emerging organically, which can be used to update training or improve routing.

No commits in the last 6 months.

Use this if you need to discover new and evolving customer service issues or common conversation topics that are not predefined in your existing systems.

Not ideal if you already have well-defined, simple categories for all your dialog intents and don't need to discover new ones.

customer-service call-center-management conversation-analysis intent-discovery customer-feedback
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

67

Forks

20

Language

Python

License

MIT

Last pushed

Jul 06, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/asappresearch/dialog-intent-induction"

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