svakulenk0/semantic_coherence

Measuring semantic (in)coherence in Ubuntu dialogue corpus using different word and knowledge graph embeddings.

23
/ 100
Experimental

This project helps researchers and data scientists analyze the semantic coherence of conversations, particularly in technical support dialogues. It takes a corpus of dialogues, processes them to identify key entities, and then generates a score indicating how semantically related the utterances are. It is designed for those studying communication patterns or developing conversational AI.

No commits in the last 6 months.

Use this if you need to quantify how well different parts of a conversation stick to a central topic or if you are evaluating the natural flow and logical progression of dialogue exchanges.

Not ideal if you need real-time coherence analysis for live conversations or if your primary goal is sentiment analysis or speaker identification rather than topic relatedness.

conversational-ai natural-language-understanding dialogue-analysis semantic-evaluation discourse-coherence
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 9 / 25

How are scores calculated?

Stars

18

Forks

2

Language

Python

License

Last pushed

Dec 08, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/svakulenk0/semantic_coherence"

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