Train and Infer Powerful Sentence Embeddings with AnglE | 🔥 SOTA on STS and MTEB Leaderboard

Neural network toolkit for sentence pair modeling.

PyTorch implementations of various deep learning models for paraphrase detection, semantic similarity, and textual entailment

A simple implementation of paper "HCTI at SemEval-2017 Task 1: Use convolutional neural network to evaluate semantic textual similarity."

Official Implementation of the ACL2024 Findings paper "Controllable Data Augmentation for Few-Shot Text Mining with Chain-of-Thought Attribute Manipulation"

Sentence Similarity Estimator (SenSim)

Official implementation of: Tha3aroon at NSURL-2019 Task 8: Semantic Question Similarity in Arabic

Similarity Learning applied to Speaker Verification and Semantic Textual Similarity

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.

Performs contextual, fully supervised text normalization

Semantic Textual Similarity and Dialogue System package for Python

Development and Application of Document Embedding for Semantic Text Retrieval

Telegram bot with which teenagers can freely ask questions about reproductive health and sex education.

ISCC - Semantic Code Text

Implementation of a Siamese LSTM for Semantic Textual Similarity task.

Semantic Textual Similarity and Dialogue System package for Python

Mail Receptionist (COVID-19 Ausgabe) sortiert Ihre eMail-Anfragen bzgl. einer COVID-19 Impfung vollautomatisch ein bzw. aus und versendet auf Wunsch zusätzlich eine Antwort an den Absender. So bleibt Ihnen mehr Zeit für Ihre Patienten oder die Anstellung von Extra-Mitarbeitern zur Bewältigung der Mailflut entfällt.

Our lexical similarity measures, as employed in http://propor2016.di.fc.ul.pt/wp-content/uploads/2016/07/ASSIN_2016_paper_4.pdf

Elevated solutions LLC's proof of concept work on STS work for ease in document look up.

This is an API for plagiarism detection in essays. It is based on the sentence-transformers library and the paraphrase-multilingual-MiniLM-L12-v2 model.