思想来自于苏神 GlobalPointer，原始版本是基于keras实现的，模型结构实现参考现有 pytorch 复现代码【感谢!】，基于torch百分百复现苏神原始效果。
中文医学命名实体数据集 点这里申请，很简单，共包含九类医学实体
python 3.8.1
pytorch==1.8.1
transformer==4.9.2
tqdm
numpy
1、笔者比较喜欢用RoBerta系列 RoBERTa-zh-Large-PyTorch
2、点这里直接goole drive下载
注意把train/predict文件中的 bert_model_path 路径改为你自己的
python train_CME.py
python predict_CME.py
苏神的模型效果还是不错的！
GPT2-NewsTitle 带有超详细注释的GPT2新闻标题生成项目 UpDate 01.02.2021 从网上收集数据，将清华新闻数据、搜狗新闻数据等新闻数据集，以及开源的一些摘要数据进行整理清洗，构建一个较完善的中文摘要数据集。 数据集清洗时，仅进行了简单地规则清洗。
Cherche (search in French) allows you to create a neural search pipeline using retrievers and pre-trained language models as rankers. Cherche is meant to be used with small to medium sized corpora. C
KR-BERT-SimCSE Implementing SimCSE(paper, official repository) using TensorFlow 2 and KR-BERT. Training Unsupervised python train_unsupervised.py --mi
✨A Python framework to explore, label, and monitor data for NLP projects
ttslearn: Library for Pythonで学ぶ音声合成 (Text-to-speech with Python) 日本語は以下に続きます (Japanese follows) English: This book is written in Japanese and primaril
Word Counter By EBUS Coding Club Count the frequency of letters or words in a text file and show a graph. Requirements Python 3.9 or higher matplotlib
textgenrnn Easily train your own text-generating neural network of any size and complexity on any text dataset with a few lines of code, or quickly tr
JaQuAD: Japanese Question Answering Dataset for Machine Reading Comprehension (2022, Skelter Labs)
A Python package implementing a new model for text classification with visualization tools for Explainable AI 🍣 Online live demos: http://tworld.io/s
Basic Code 1. Use The Code Configuration Environment conda create -n code_base p
Dedupe Python Library dedupe is a python library that uses machine learning to perform fuzzy matching, deduplication and entity resolution quickly on
Date-Extraction-from-Contracts This is a NLP based project to extract effective date of the contract from their text files. Problem statement This is
Easy-Translate is a script for translating large text files in your machine using the M2M100 models from Facebook/Meta AI. We also privide a script fo
This repository contains slides for the course "20-00-0947: Deep Learning for Natural Language Processing" (Technical University of Darmstadt, Summer term 2021).
Tokenizer Le Tokenizer est un analyseur lexicale, il permet, comme Flex and Yacc par exemple, de tokenizer du code, c'est à dire transformer du code e
Sequence labeler This is a neural network sequence labeling system. Given a sequence of tokens, it will learn to assign labels to each token. Can be u
Implementation of Deep-Forecast using PyTorch Deep Forecast: Deep Learning-based Spatio-Temporal Forecasting Adapted from original implementation Setu
Simple NLP based project without any use of AI
Camphr - spaCy plugin for Transformers, Udify, Elmo, etc. Camphr is a Natural Language Processing library that helps in seamless integration for a wid
blurr A library that integrates huggingface transformers with version 2 of the fastai framework Install You can now pip install blurr via pip install
785 Dec 29, 2022
224 Nov 29, 2022
27 Dec 12, 2022
1.5k Jan 02, 2023
189 Dec 29, 2022
0 Apr 09, 2022
4.8k Dec 30, 2022
84 Dec 27, 2022
285 Jan 02, 2023
1 Jan 04, 2022
3.6k Jan 02, 2023
1 Jan 26, 2022
41 Dec 15, 2022
0 Feb 21, 2022
1 Aug 15, 2022
250 Nov 03, 2022
151 Dec 14, 2022
1 Apr 26, 2022
342 Nov 21, 2022
253 Dec 31, 2022