perceptiveshawty/CompCSE
Code for the ACL 2023 long paper "Composition-contrastive Learning for Sentence Embeddings"
This project helps machine learning engineers or NLP researchers build more effective text embedding models. It takes unlabeled text data and uses a composition-contrastive learning method to generate high-quality sentence embeddings, which are numerical representations of text that capture semantic meaning. This is useful for tasks like semantic search, text similarity, or clustering.
No commits in the last 6 months.
Use this if you are a machine learning engineer or NLP researcher looking to train strong sentence embedding models from unlabeled data with a parameter-efficient approach.
Not ideal if you are looking for a pre-built solution for text analysis and don't have experience with machine learning model training or Python.
Stars
7
Forks
—
Language
Python
License
—
Category
Last pushed
Jul 25, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/perceptiveshawty/CompCSE"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
princeton-nlp/SimCSE
[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821
n-waves/multifit
The code to reproduce results from paper "MultiFiT: Efficient Multi-lingual Language Model...
yxuansu/SimCTG
[NeurIPS'22 Spotlight] A Contrastive Framework for Neural Text Generation
alibaba-edu/simple-effective-text-matching
Source code of the ACL2019 paper "Simple and Effective Text Matching with Richer Alignment Features".
Shark-NLP/OpenICL
OpenICL is an open-source framework to facilitate research, development, and prototyping of...