microsoft/vert-papers

This repository contains code and datasets related to entity/knowledge papers from the VERT (Versatile Entity Recognition & disambiguation Toolkit) project, by the Knowledge Computing group at Microsoft Research Asia (MSRA).

50
/ 100
Established

This project offers research code and datasets for advanced natural language processing tasks focused on understanding entities. It takes raw text or tabular data as input and aims to precisely identify and link real-world entities mentioned within it, like people, organizations, or locations. Information architects, data scientists, and AI researchers working on knowledge base construction or complex data interpretation would find this beneficial.

281 stars. No commits in the last 6 months.

Use this if you need to extract and connect specific entities from unstructured text or interpret the meaning of data within tables, especially across different languages.

Not ideal if you are looking for a ready-to-use, off-the-shelf application rather than research-oriented code and datasets for experimentation.

knowledge-graph-construction natural-language-understanding data-entity-extraction semantic-table-interpretation cross-lingual-information-retrieval
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

281

Forks

97

Language

Python

License

MIT

Last pushed

Mar 16, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/microsoft/vert-papers"

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