There are 5 repositories under bert-embeddings topic.
Infinity is a high-throughput, low-latency REST API for serving vector embeddings, supporting a wide range of text-embedding models and frameworks.
PhoBERT: Pre-trained language models for Vietnamese (EMNLP-2020 Findings)
💭 Aspect-Based-Sentiment-Analysis: Transformer & Explainable ML (TensorFlow)
NLP for human. A fast and easy-to-use natural language processing (NLP) toolkit, satisfying your imagination about NLP.
Fast + Non-Autoregressive Grammatical Error Correction using BERT. Code and Pre-trained models for paper "Parallel Iterative Edit Models for Local Sequence Transduction": www.aclweb.org/anthology/D19-1435.pdf (EMNLP-IJCNLP 2019)
This repository contains PyTorch implementation for the baseline models from the paper Utterance-level Dialogue Understanding: An Empirical Study
This is a repo of basic Machine Learning what I learn. More to go...
Electra pre-trained model using Vietnamese corpus
Novel model and dataset for the task of humor detection
Implementation of ICLR 21 paper: Probing BERT in Hyperbolic Spaces
Automated Essay Scoring using BERT
This is the code for loading the SenseBERT model, described in our paper from ACL 2020.
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
Topic clustering library built on Transformer embeddings and cosine similarity metrics.Compatible with all BERT base transformers from huggingface.
An easy-to-use Python module that helps you to extract the BERT embeddings for a large text dataset (Bengali/English) efficiently.
BERT semantic search engine for searching literature research papers for coronavirus covid-19 in google colab
A Robustly Optimized BERT Pretraining Approach for Vietnamese
COVID-19 Question Dataset from the paper "What Are People Asking About COVID-19? A Question Classification Dataset"
Code and CoarseWSD-20 datasets for "Language Models and Word Sense Disambiguation: An Overview and Analysis"
Fast and memory-efficient library for WordPiece tokenization as it is used by BERT.
Finetuning BERT in PyTorch for sentiment analysis.
Contextual knowledge bases
Problem Statement: Given the tweets from customers about various tech firms who manufacture and sell mobiles, computers, laptops, etc, the task is to identify if the tweets have a negative sentiment towards such companies or products.
Recommendation engine framework based on Wikipedia data
A showcase of combining Elasticsearch with BERT on the HackerNews public data
YouTube GPT is an Android app that allows users to generate video summaries using A.I models. Also capable of answering cross-questions related to the video content!
Content based recommender system for books using NLP.
PyTorch Implementation of VQA Baseline & Hierarchical Co-Attention model
Small tutorial on how you can use BERT for Topic Modeling
C++ inference wrappers for running blazing fast embedding services on your favourite serverless like AWS Lambda. By Prithivi Da, PRs welcome.