SAP-samples/acl2023-micse
Source code for ACL 2023 paper "miCSE: Mutual Information Contrastive Learning for Low-shot Sentence Embeddings".
This project helps machine learning engineers and researchers create high-quality numerical representations (embeddings) of sentences, even when they have very little training data. It takes a collection of English sentences and outputs a fine-tuned language model capable of generating these robust sentence embeddings. This is particularly useful for those developing natural language processing applications with limited data resources.
No commits in the last 6 months.
Use this if you need to train a sentence embedding model efficiently with only a small amount of labeled data, aiming for state-of-the-art performance in low-shot learning scenarios.
Not ideal if you already have a large, diverse dataset for training your sentence embedding model, as its primary advantage is in data-scarce situations.
Stars
9
Forks
2
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 07, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/SAP-samples/acl2023-micse"
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...