CRLT: A Unified Contrastive Learning Toolkit for Unsupervised Text Representation Learning
-
Updated
Feb 5, 2022 - Python
CRLT: A Unified Contrastive Learning Toolkit for Unsupervised Text Representation Learning
Scripts, data, and results from the "Through time with BERT" project, which evaluated and examined the extent to which English tenses are represented in BERT's raw sentence embeddings.
🚀 EASE-ReD: Ethnicity Analysis and Sentence Embedding from Restaurant Distribution. Predicting ethnicity distribution in an area based on its restaurants data. Cleaning the data using sentence embeddings!
Kirli veri çekildiğinde ön işleme adımlarına gerek kalmadan model eğitimi için hazır hale getirmek amacıyla yapılan uygulamadır.
Finding of ACL2023: Clustering-Aware Negative Sampling for Unsupervised Sentence Representation
C++ implementation of the paper "Segmentation-free compositional n-gram embedding". NAACL-HLT2019.
A project aiming to leverage text embeddings and Milvus, a high-performance vector search engine, to detect duplicate job postings.
[NAACL(2019)] Generating Knowledge Graph Paths from Textual Definitions using Sequence-to-Sequence Models
Difference-based Contrastive Learning for Korean Sentence Embeddings
Official implementation for paper "Learning Discrete Sentence Representations via Construction & Decomposition".
EmbedRank implemented in Python.
Run sentence-transformers (SBERT) compatible models in Node.js or browser.
HASHET (HAshtag recommendation using Sentence-to-Hashtag Embedding Translation) is a model aimed at suggesting a relevant set of hashtags for a given post.
Benchmark for Thai sentence representation
Paraphrase Generation model using pair-wise discriminator loss
Korean Sentence Embedding Repository
Train and Infer Powerful Sentence Embeddings with AnglE | 🔥 SOTA on STS and MTEB Leaderboard
This repository contains various ways to calculate sentence vector similarity using NLP models
Add a description, image, and links to the sentence-embedding topic page so that developers can more easily learn about it.
To associate your repository with the sentence-embedding topic, visit your repo's landing page and select "manage topics."