DolbyUUU/Reinforcement-Calibration-SimCSE
Reinforcement Calibration SimCSE, combining contrastive learning, artificial potential fields, perceptual loss, and RLHF to achieve improved Semantic Textual Similarity (STS) embeddings. PyTorch-based implementations of PerceptualBERT and ForceBasedInfoNCE, along with fine-tuning capabilities via RLHF and evaluation using SentEval.
If you work with text data and need to precisely measure how similar the meaning of different sentences is, this tool helps you create highly accurate sentence embeddings. It takes your raw text sentences as input and produces numerical representations that capture their semantic content more effectively. This is for NLP practitioners, data scientists, or researchers who need to quantify sentence meaning for tasks like document clustering, search, or content recommendation.
No commits in the last 6 months.
Use this if you need to generate high-quality numerical representations of sentences for Semantic Textual Similarity (STS) tasks and are looking for methods that incorporate human feedback.
Not ideal if you are looking for a pre-trained, ready-to-use model without any fine-tuning or if your primary need is not focused on semantic similarity.
Stars
11
Forks
—
Language
Python
License
—
Category
Last pushed
Dec 24, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/DolbyUUU/Reinforcement-Calibration-SimCSE"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
n-waves/multifit
The code to reproduce results from paper "MultiFiT: Efficient Multi-lingual Language Model...
princeton-nlp/SimCSE
[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821
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...