Natural Language Processing

Use OpenAI's CLIP neural network to search inside YouTube videos. You can try it by running the notebook on Google Colab.

This repository contains the source code of BEBLID: Boosted Efficient Binary Local Image Descriptor

NLP progress in Fintech. A repository to track the progress in Natural Language Processing (NLP) related to the domain of Finance, including the datasets, papers, and current state-of-the-art results for the most popular tasks.

This package wraps the Stanza (formerly StanfordNLP) library, so you can use Stanford's models as a spaCy pipeline.

Code and data to support the paper "PAQ 65 Million Probably-Asked Questions andWhat You Can Do With Them"

Open Source Annotation Tools for Computer Vision and NLP tasks

This repo contains a code and a few results of my experiments with StyleGAN and CLIP. Let's call it StyleCLIP. Given a textual description, my goal was to edit a given image, or generate one.

本リポジトリはAnnanAIによる「AllenNLP入門」のソースコード置き場です。AmazonまたはBOOTHにて販売中です。

Official PyTorch code for ClipBERT, an efficient framework for end-to-end learning for image-text and video-text tasks.

A multi-entity Transformer for multi-agent spatiotemporal modeling.

中文版unilm预训练模型

mindspore-nlp-tutorial is a tutorial for who is studying NLP(Natural Language Processing) using MindSpore. This repository is migrated from nlp-tutorial. Most of the models in NLP were migrated from Pytorch version with less than

NLP Core Library and Model Zoo based on PaddlePaddle 2.0

一份中文综述文章列表（自然语言处理&机器学习）

A neural named entity recognition and multi-type normalization tool for biomedical text mining

Code for the paper "Partially-Aligned Data-to-Text Generation with Distant Supervision" in EMNLP 2020.

FBTT-Embedding library provides functionality to compress sparse embedding tables commonly usedin machine learning models such as recommendation and natural language processing.

Pororo: A Deep Learning based Multilingual Natural Language Processing Library

Although early text-to-speech (TTS) models such as Tacotron 2 have succeeded in generating human-like speech, their autoregressive architectures

Easy to use, state-of-the-art Neural Machine Translation for 100+ languages

Code of paper: A Recurrent Vision-and-Language BERT for Navigation

Awesome Pretrained Chinese NLP Models，高质量中文预训练模型集合

[ICLR 2021] "InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective" by Boxin Wang, Shuohang Wang, Yu Cheng, Zhe Gan, Ruoxi Jia, Bo Li, Jingjing Liu

Search photos on Unsplash using natural language descriptions. The search is powered by OpenAI's CLIP model and the Unsplash Dataset.

Interactive Jupyter Notebook Environment for using the GPT-3 Instruct API

Reranker is a lightweight, effective and efficient package for training and deploying deep languge model reranker in information retrieval (IR), question answering (QA) and many other natural language processing (NLP) pipelines

Unilm for Chinese Chitchat Robot.

pyAudioDspTools is a python 3 package for manipulating audio by just using numpy. This can be from a .wav or as a stream via pyAudio for example. pyAudioDspTool's only requirement is Numpy.

Apple-M1-BERT Inference

OCR DB including Korean

Tensorflow implementation of the Vision Transformer (ViT) presented in An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale, where the authors show that Transformers applied directly to image patches and pre-

Distributed advertisement-based BTLE presence detection reported via mqtt

CRSLab is an open-source toolkit for building Conversational Recommender System (CRS). It is developed based on Python and PyTorch.