EMNLP 2022 "PCL: Peer-Contrastive Learning with Diverse Augmentations for Unsupervised Sentence Embeddings"
-
Updated
Jul 31, 2023 - Python
EMNLP 2022 "PCL: Peer-Contrastive Learning with Diverse Augmentations for Unsupervised Sentence Embeddings"
Streamlit web application for tc*, a tool that can be used to flag non-standard clauses in Terms & Conditions agreements.
Semantic similarity methodolgies including multilingual appraoches
The project aims to help job seekers understand the essential qualifications required for specific jobs and assess how well their skills match those positions. Additionally, it assists recruiters in improving their resume selection processes by analyzing and comprehending job advertisements.
Predicting similarity of texts using transformers
Several recent models are implemented for Chinese STS task (Semantic Textual Similarity).
SBERT - Sentence Similarity Matching
This tool analyzes input text and suggests improvements based on semantic similarity to a list of standard phrases. It provides both a command-line interface (CLI) and a simple web-based user interface (UI).
NLP related concepts, challenges and datasets
Measure sentence similarity by using word2vec
Semantic Sentence Similarity using Word2Vec, Fasttext embedding and Cosine Similarity, Word Mover Distance
This code is based on an unfinished paper of mine that uses a version of topological sorting and WordNet to perform extraction based summarization of a corpus.
This repository contains python script for calculating Longest Common Subsequences (LSC) between tokenized URDU sentences.
My bachelor degree paper, presentation and code
Sentence similarity between sentences or paragraphs: flask API + streamlit app.
A tool to map FrameNet Lexical Units to BabelNet synsets using the distance between sentence embeddings of corresponding definitions
Payment Matching Notebook for Shopee Code League Competition
Add a description, image, and links to the sentence-similarity topic page so that developers can more easily learn about it.
To associate your repository with the sentence-similarity topic, visit your repo's landing page and select "manage topics."