NathanDuran/Probabilistic-RNN-DA-Classifier

Probabilistic Dialogue Act Classification for the Switchboard Corpus using an LSTM model

40
/ 100
Emerging

This project helps conversational AI developers and researchers automatically classify spoken dialogue acts in a conversation. It takes raw text from a dialogue, like a customer service call or meeting transcript, and outputs the probability that each utterance serves a specific purpose (e.g., 'question', 'statement', 'agreement'). This is primarily for those building or analyzing dialogue systems, especially in academic or research settings.

No commits in the last 6 months.

Use this if you need to automatically categorize the communicative intent of utterances within a conversation, particularly for research on dialogue systems or spoken language understanding.

Not ideal if you need a pre-built, production-ready solution for real-time dialogue act classification in a commercial application without significant development work.

conversational-ai dialogue-systems natural-language-understanding speech-analysis computational-linguistics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

24

Forks

13

Language

Python

License

GPL-3.0

Last pushed

Jul 30, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/NathanDuran/Probabilistic-RNN-DA-Classifier"

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