Natural Language Processing

A reading list of up-to-date papers on NLP for Social Good.

Idea is to build a model which will take keywords as inputs and generate sentences as outputs.

Implementation of ResMLP, an all MLP solution to image classification out of Facebook AI, in Pytorch

COVID-19 outbreak has become a global pandemic. NLP researchers are fighting the epidemic in their own way.

🏆 The 1st Place Submission to AICity Challenge 2021 Natural Language-Based Vehicle Retrieval Track (Alibaba-UTS submission)

The projects lets you extract glossary words and their definitions from a given piece of text automatically using NLP techniques

An All-MLP solution for Vision, from Google AI, in Pytorch.

YSDA course in Speech Processing.

Identify the emotion of multiple speakers in an Audio Segment

Text classification tasks are most easily encountered in the area of natural language processing and can be used in various ways.

An Easy-to-use, Modular and Prolongable package of deep-learning based Named Entity Recognition Models.

All the goto functions you need to handle NLP use-cases, integrated in NLPretext

Negative Sampling for NER Unlabeled entity problem is prevalent in many NER scenarios (e.g., weakly supervised NER). Our paper in ICLR-2021 proposes u

SummVis is an interactive visualization tool for text summarization systems, supporting analysis of models, data, and evaluation metrics.

Papers on fairness in NLP

A PyTorch-based toolkit for natural language processing

Creative NLG and Computational Creativity is becoming popular more so with the advent of Language Models. We hope to provide a list of great papers that can serve as a reference for researchers interested in such topics. This repo

This repository contains the code and pre-trained models for our paper SimCSE: Simple Contrastive Learning of Sentence Embeddings.

Labelled data remains a scarce resource in many practical NLP scenarios. This is especially the case when working with resource-poor languages (or text domains), or when using task-specific labels without pre-existing datasets

Text Extensions for Pandas turns Pandas DataFrames into a universal data structure for representing intermediate data in all phases of your NLP application development workflow.

This is a container wrapping OpenAI's CLIP model in a RESTful interface.

端到端的长本文摘要模型（法研杯2020司法摘要赛道）

ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training

PlenOctrees_NeRF-SH This is an implementation of the Paper PlenOctrees for Real-time Rendering of Neural Radiance Fields. Not only the code provides t

Obsei is intended to be an automation tool for text analysis need.

FedNLP is a research-oriented benchmarking framework for advancing federated learning (FL) in natural language processing (NLP). It uses FedML repository as the git submodule. In other words, FedNLP only focuses on adavanced model

OpenAI CLIP text encoders for multiple languages!

PyTorch Lightning is the lightweight PyTorch wrapper for high-performance AI research. PyTorch is extremely easy to use to build complex AI models. But once the research gets complicated and things like multi-GPU training, 16-bit

Automated Phrase Mining from Massive Text Corpora in Python.

공개된 한국어 Transformer 계열 모델들은 대부분 한국어 위키, 뉴스 기사, 책 등 잘 정제된 데이터를 기반으로 학습한 모델입니다. 한편, 실제로 NSMC와 같은 User-Generated Noisy text domain 데이터셋은 정제되지 않았고 구어체 특징에 신조어가 많으며, 오탈자 등 공식적인 글쓰기에서 나타나지 않는 표현들이 빈번하게 등장합니다.

Label data using HuggingFace's transformers and automatically get a prediction service

This repo contains implementation of different architectures for emotion recognition in conversations.

Megatron (1 and 2) is a large, powerful transformer developed by the Applied Deep Learning Research team at NVIDIA. This repository is for ongoing research on training large transformer language models at scale. We developed effic