zjunlp/SPEECH

[ACL 2023] SPEECH: Structured Prediction with Energy-Based Event-Centric Hyperspheres

27
/ 100
Experimental

This project helps you automatically identify and categorize real-world events mentioned in documents, and then discover the relationships between them. For example, it can find all mentions of "product launch" and then determine if one launch caused another, or if they happened simultaneously. It takes unstructured text documents as input and outputs structured information about events and their temporal, causal, or sub-event relationships. This is useful for researchers or analysts working with large volumes of text data who need to extract and understand complex event structures.

No commits in the last 6 months.

Use this if you need to automatically extract and understand the complex relationships between events mentioned across multiple documents, such as identifying causes and effects, or sequences of events.

Not ideal if you're looking for a simple keyword extraction tool or if your primary need is to classify the sentiment of text rather than the structure of events.

event-extraction document-analysis information-extraction text-analytics causal-inference
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

13

Forks

1

Language

Python

License

MIT

Last pushed

Dec 22, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/zjunlp/SPEECH"

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