Chinese NER with albert/electra or other bert descendable model (keras)

Overview

Chinese NLP (albert/electra with Keras)

Named Entity Recognization

Project Structure

./
├── NER
│   ├── __init__.py
│   ├── log                                     训练nohup日志
│   │   ├── albert.out
│   │   ├── albert_crf.out
│   │   ├── electra.out
│   │   ├── electra_crf.out
│   │   ├── electra_regulization.out
│   │   └── electra_tiny.out
│   └── train.py
├── README.md
├── albert_base_google_zh                       albert_base权重
│   ├── albert_config.json
│   ├── albert_model.ckpt.data-00000-of-00001
│   ├── albert_model.ckpt.index
│   ├── checkpoint
│   └── vocab.txt
├── albert_tiny_google_zh                       albert_tiny权重
│   ├── albert_config.json
│   ├── albert_model.ckpt.data-00000-of-00001
│   ├── albert_model.ckpt.index
│   ├── checkpoint
│   └── vocab.txt
├── chinese_electra_small_ex_L-24_H-256_A-4     electra_small权重
│   ├── electra_small_ex.data-00000-of-00001
│   ├── electra_small_ex.index
│   ├── electra_small_ex.meta
│   ├── small_ex_discriminator_config.json
│   ├── small_ex_generator_config.json
│   └── vocab.txt
├── data                                        数据集
│   ├── pulmonary.test
│   ├── pulmonary.train
│   └── sict_train.txt
├── electra_180g_base                           electra_base权重
│   ├── base_discriminator_config.json
│   ├── base_generator_config.json
│   ├── electra_180g_base.ckpt.data-00000-of-00001
│   ├── electra_180g_base.ckpt.index
│   ├── electra_180g_base.ckpt.meta
│   └── vocab.txt
├── environment.yaml                            conda环境配置文件
├── main.py
├── path.py                                     所有路径
├── requirements.txt
├── utils                                       bert4keras包(也可pip下)
│   ├── __init__.py
│   ├── backend.py
│   ├── layers.py
│   ├── models.py
│   ├── optimizers.py
│   ├── snippets.py
│   └── tokenizers.py
└── weights                                     权重文件
    ├── pulmonary_albert_ner.h5
    ├── pulmonary_electra_ner.h5
    └── pulmonary_electra_tiny_ner_crf.h5

9 directories, 48 files

Dataset

三甲医院肺结节数据集,20000+字,BIO格式,形如:

中	B-ORG
共	I-ORG
中	I-ORG
央	I-ORG
致	O
中	B-ORG
国	I-ORG
致	I-ORG
公	I-ORG
党	I-ORG
十	I-ORG
一	I-ORG
大	I-ORG
的	O
贺	O
词	O

ATTENTION: 在处理自己数据集的时候需要注意:

  • 字与标签之间用空格("\ ")隔开
  • 其中句子与句子之间使用空行隔开

Steps

  1. 替换数据集
  2. 修改NER/train.py中的maxlen(超过截断,少于填充,最好设置训练集、测试集中最长句子作为MAX_SEQ_LEN)
  3. 下载权重,放到项目中
  4. 修改path.py中的地址
  5. 根据需要修改NER/train.py模型结构
  6. 训练前debug看下train_generator数据
  7. 训练

Model

albert

electra

Train

运行NER/train.py

Evaluate

train时给出的F1即为实体级别的F1

albert最佳F1

Epoch 61/300
13/13 [==============================] - 16s 1s/step - loss: 0.1343 - sparse_accuracy: 0.9713
test:  f1: 0.82428, precision: 0.81775, recall: 0.83092

electra

Epoch 29/300
13/13 [==============================] - 16s 1s/step - loss: 0.3487 - sparse_accuracy: 0.9146
test:  f1: 0.83189, precision: 0.81579, recall: 0.84863
Official PyTorch implementation of "Dual Path Learning for Domain Adaptation of Semantic Segmentation".

Dual Path Learning for Domain Adaptation of Semantic Segmentation Official PyTorch implementation of "Dual Path Learning for Domain Adaptation of Sema

27 Dec 22, 2022
Code for CodeT5: a new code-aware pre-trained encoder-decoder model.

CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation This is the official PyTorch implementation

Salesforce 564 Jan 08, 2023
Shirt Bot is a discord bot which uses GPT-3 to generate text

SHIRT BOT · Shirt Bot is a discord bot which uses GPT-3 to generate text. Made by Cyclcrclicly#3420 (474183744685604865) on Discord. Support Server EX

31 Oct 31, 2022
this repository has datasets containing information of Uber pickups in NYC from April 2014 to September 2014 and January to June 2015. data Analysis , virtualization and some insights are gathered here

uber-pickups-analysis Data Source: https://www.kaggle.com/fivethirtyeight/uber-pickups-in-new-york-city Information about data set The dataset contain

1 Nov 02, 2021
Python api wrapper for JellyFish Lights

Python api wrapper for JellyFish Lights The hope is to make this a pip installable package Current capabalilities: Connects to a local JellyFish Light

10 Dec 18, 2022
Use the state-of-the-art m2m100 to translate large data on CPU/GPU/TPU. Super Easy!

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

Iker García-Ferrero 41 Dec 15, 2022
NLPIR tutorial: pretrain for IR. pre-train on raw textual corpus, fine-tune on MS MARCO Document Ranking

pretrain4ir_tutorial NLPIR tutorial: pretrain for IR. pre-train on raw textual corpus, fine-tune on MS MARCO Document Ranking 用作NLPIR实验室, Pre-training

ZYMa 12 Apr 07, 2022
Partially offline multi-language translator built upon Huggingface transformers.

Translate Command-line interface to translation pipelines, powered by Huggingface transformers. This tool can download translation models, and then us

Richard Jarry 8 Oct 25, 2022
Modeling cumulative cases of Covid-19 in the US during the Covid 19 Delta wave using Bayesian methods.

Introduction The goal of this analysis is to find a model that fits the observed cumulative cases of COVID-19 in the US, starting in Mid-July 2021 and

Alexander Keeney 1 Jan 05, 2022
Utilities for preprocessing text for deep learning with Keras

Note: This utility is really old and is no longer maintained. You should use keras.layers.TextVectorization instead of this. Utilities for pre-process

Hamel Husain 180 Dec 09, 2022
This is the 25 + 1 year anniversary version of the 1995 Rachford-Rice contest

Rachford-Rice Contest This is the 25 + 1 year anniversary version of the 1995 Rachford-Rice contest. Can you solve the Rachford-Rice problem for all t

13 Sep 20, 2022
Natural language Understanding Toolkit

Natural language Understanding Toolkit TOC Requirements Installation Documentation CLSCL NER References Requirements To install nut you need: Python 2

Peter Prettenhofer 119 Oct 08, 2022
Fake news detector filters - Smart filter project allow to classify the quality of information and web pages

fake-news-detector-1.0 Lists, lists and more lists... Spam filter list, quality keyword list, stoplist list, top-domains urls list, news agencies webs

Memo Sim 1 Jan 04, 2022
Hierarchical unsupervised and semi-supervised topic models for sparse count data with CorEx

Anchored CorEx: Hierarchical Topic Modeling with Minimal Domain Knowledge Correlation Explanation (CorEx) is a topic model that yields rich topics tha

Greg Ver Steeg 592 Dec 18, 2022
GPT-3: Language Models are Few-Shot Learners

GPT-3: Language Models are Few-Shot Learners arXiv link Recent work has demonstrated substantial gains on many NLP tasks and benchmarks by pre-trainin

OpenAI 12.5k Jan 05, 2023
Concept Modeling: Topic Modeling on Images and Text

Concept is a technique that leverages CLIP and BERTopic-based techniques to perform Concept Modeling on images.

Maarten Grootendorst 120 Dec 27, 2022
A tool helps build a talk preview image by combining the given background image and talk event description

talk-preview-img-builder A tool helps build a talk preview image by combining the given background image and talk event description Installation and U

PyCon Taiwan 4 Aug 20, 2022
Based on 125GB of data leaked from Twitch, you can see their monthly revenues from 2019-2021

Twitch Revenues Bu script'i kullanarak istediğiniz yayıncıların, Twitch'den sızdırılan 125 GB'lik veriye dayanarak, 2019-2021 arası aylık gelirlerini

4 Nov 11, 2021
(ACL-IJCNLP 2021) Convolutions and Self-Attention: Re-interpreting Relative Positions in Pre-trained Language Models.

BERT Convolutions Code for the paper Convolutions and Self-Attention: Re-interpreting Relative Positions in Pre-trained Language Models. Contains expe

mlpc-ucsd 21 Jul 18, 2022
This is the source code of RPG (Reward-Randomized Policy Gradient)

RPG (Reward-Randomized Policy Gradient) Zhenggang Tang*, Chao Yu*, Boyuan Chen, Huazhe Xu, Xiaolong Wang, Fei Fang, Simon Shaolei Du, Yu Wang, Yi Wu (

40 Nov 25, 2022