alibaba/SimCSE-with-CARDS
Source code for SIGIR 2022 paper.
This project helps machine learning engineers and researchers improve the quality of sentence embeddings for natural language processing tasks. By applying 'case-switched' positive examples and carefully selected 'hard negative' examples during model training, it enhances how well models understand the meaning of sentences. The result is better performance on tasks like semantic similarity and natural language inference, benefiting anyone building or evaluating NLP systems.
No commits in the last 6 months.
Use this if you are a machine learning engineer or researcher looking to build more robust and accurate sentence embedding models for natural language processing applications.
Not ideal if you are an end-user without a technical background in machine learning and NLP, as this is a developer-focused tool for model training.
Stars
16
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Apr 25, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/alibaba/SimCSE-with-CARDS"
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...