experiments of some semantic matching models and comparison of experimental results.

天池阿里灵杰问天引擎电商搜索算法赛非官方 baseline，又名 NLP 从入门到 22/2771。

Transformer-based models implemented in tensorflow 2.x(using keras).

文本相似度，语义向量，文本向量，text-similarity，similarity, sentence-similarity，BERT，SimCSE，BERT-Whitening，Sentence-BERT, PromCSE, SBERT

Exploring Japanese SimCSE

Implementation of "RankCSE: Unsupervised Sentence Representation Learning via Learning to Rank" (ACL 2023)

This is a hands-on for ML beginners to perform SimCSE step-by-step. Implemented both supervised SimCSE and unsupervisied SimCSE, and distributed training is possible with Amazon SageMaker.

A TensorFlow 2 Keras implementation of SimCSE with unsupervised and supervised.

Extract Molecular SMILES embeddings from language models pre-trained with various objectives architectures.

A Keras-based and TensorFlow-backend NLP Models Toolkit.

Sentence Embeddings using Deep Nerual Networks in PRODUCTION!

CRLT: A Unified Contrastive Learning Toolkit for Unsupervised Text Representation Learning

Domain adaption for an embedding model using unsupervised and supervised finetuning on scientific texts for the SciFact retrieval task.

Data pipelines for both TensorFlow and PyTorch!