vered1986/NC_embeddings
Comparison between various noun compound embeddings
This project helps natural language processing researchers compare different ways of representing English noun compounds, like "coffee break" or "data science." It takes a corpus of text (like Wikipedia) and a list of noun compounds, and outputs various numerical representations (embeddings) of these compounds. The primary users are researchers in computational linguistics or natural language processing interested in lexical semantics.
No commits in the last 6 months.
Use this if you are an NLP researcher and want to train and evaluate different noun compound embedding models for tasks like classification or qualitative analysis.
Not ideal if you need to identify or extract noun compounds from text, as this tool assumes you already have a list.
Stars
10
Forks
2
Language
Python
License
—
Category
Last pushed
Jun 13, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/vered1986/NC_embeddings"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
embeddings-benchmark/mteb
MTEB: Massive Text Embedding Benchmark
harmonydata/harmony
The Harmony Python library: a research tool for psychologists to harmonise data and...
yannvgn/laserembeddings
LASER multilingual sentence embeddings as a pip package
embeddings-benchmark/results
Data for the MTEB leaderboard
Hironsan/awesome-embedding-models
A curated list of awesome embedding models tutorials, projects and communities.