satya77/Entity_Embedding
Reference implementation of the paper "Word Embeddings for Entity-annotated Texts"
When analyzing large volumes of text, understanding the meaning and relationships between both common words and specific entities like people, organizations, or locations is crucial. This project helps you generate specialized 'entity embeddings' that represent these named entities alongside regular words. You input an annotated text corpus (like news articles where entities are tagged) and get out vector representations that capture semantic similarity for both words and entities, which can then be used in downstream text analysis tasks by data scientists or researchers.
No commits in the last 6 months.
Use this if you need to analyze text where named entities are particularly important and you want to capture their relationships and meanings more accurately than traditional word embedding methods.
Not ideal if your text data is not annotated with named entities, or if your primary focus is solely on general word semantics without needing to distinguish specific entities.
Stars
18
Forks
1
Language
Python
License
—
Category
Last pushed
Apr 12, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/satya77/Entity_Embedding"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MilaNLProc/contextualized-topic-models
A python package to run contextualized topic modeling. CTMs combine contextualized embeddings...
vinid/cade
Compass-aligned Distributional Embeddings. Align embeddings from different corpora
spcl/ncc
Neural Code Comprehension: A Learnable Representation of Code Semantics
criteo-research/CausE
Code for the Recsys 2018 paper entitled Causal Embeddings for Recommandation.
vintasoftware/entity-embed
PyTorch library for transforming entities like companies, products, etc. into vectors to support...