Weakly-supervised Text Classification Based on Keyword Graph

Overview

Weakly-supervised Text Classification Based on Keyword Graph

How to run?

Download data

Our dataset follows previous works. For long texts, we follow Conwea. For short texts, we follow LOTClass.
We transform all their data into unified json format.

  1. Download datasets from: https://drive.google.com/drive/folders/1D8E9T-vuBE-YdAd9OBy-yS4UW4AptA58?usp=sharing

    • Long text datasets(follow Conwea):

      • 20Newsgroup Fine(20NF)
      • 20Newsgroup Coarse(20NC)
      • NYT Fine(NYT_25)
      • NYT Coarse(NYT_5)
    • Short text datasets(follow LOTClass)

      • Agnews
      • dbpedia
      • imdb
      • amazon
  2. Unzip data into './data/processed'

Another way to obtain data (Not recommended):
You can download long text data from Conwea and short text data from LOTClass and transform data into json format using our code. The code is located at 'preprocess_data/process_long.py (process_short.py) You need to edit the preprocess code to change the dataset path to your downloaded path and change the taskname. The processed data is located in 'data/processed'. We alse provide preprocess code for X-class, which is 'process_x_class.py'.

Requirements

This project is based on python==3.8. The dependencies are as follow:

pytorch
DGL
yacs
visdom
transformers
scikit-learn
numpy
scipy

Train and Eval

  • Recommend to start visdom to show the results.
visdom -p 8888

Open the browser to the server_ip:8888 to show visdom panel.

  • Train:
    • First edit 'task/pipeline.py' to specify to config file and CUDA devices you used.
      Some configuration files are provided in the config folder.

    • Start training:

      python task/pipeline.py
      
    • Our code is based on multi GPUs, may be unable to run on single GPU currently.

Run on your custom dataset.

  1. provide datasets to dir data/processed.

    • keywords.json
      keywords for each class. type: dict. key: class_index. value: list containing all keywords for this class. See provided datasets for details.

    • unlabeled.json
      unlabeled sentences in our paper. type: list. item: list with 2 items([sentence_i,label_i]).
      In order to facilitate the evaluation, we are similar to Conwea's settings, where labels of sentences are provided. The labels are only used for evaluation.

  2. provide config to dir config. You can copy one of the existing config files and change some fields, like number_classes, classifier.type, data_dir_name etc.

  3. Specify the config file name in pipeline.py and run the pipeline code.

Citation

Please cite the following paper if you find our code helpful! Thank you very much.

Lu Zhang, Jiandong Ding, Yi Xu, Yingyao Liu and Shuigeng Zhou. "Weakly-supervised Text Classification Based on Keyword Graph". EMNLP 2021.

Owner
Hello_World
Computer Science at Fudan University.
Hello_World
BERT Attention Analysis

BERT Attention Analysis This repository contains code for What Does BERT Look At? An Analysis of BERT's Attention. It includes code for getting attent

Kevin Clark 401 Dec 11, 2022
A Plover python dictionary allowing for consistent symbol input with specification of attachment and capitalisation in one stroke.

Emily's Symbol Dictionary Design This dictionary was created with the following goals in mind: Have a consistent method to type (pretty much) every sy

Emily 68 Jan 07, 2023
Lightweight utility tools for the detection of multiple spellings, meanings, and language-specific terminology in British and American English

Breame ( British English and American English) Breame is a lightweight Python package with a number of utility tools to aid in the detection of words

Charles 8 Oct 10, 2022
hashily is a Python module that provides a variety of text decoding and encoding operations.

hashily is a python module that performs a variety of text decoding and encoding functions. It also various functions for encrypting and decrypting text using various ciphers.

DevMysT 5 Jul 17, 2022
Athena is an open-source implementation of end-to-end speech processing engine.

Athena is an open-source implementation of end-to-end speech processing engine. Our vision is to empower both industrial application and academic research on end-to-end models for speech processing.

Ke Technologies 34 Sep 08, 2022
ASCEND Chinese-English code-switching dataset

ASCEND (A Spontaneous Chinese-English Dataset) introduces a high-quality resource of spontaneous multi-turn conversational dialogue Chinese-English code-switching corpus collected in Hong Kong.

CAiRE 11 Dec 09, 2022
End-2-end speech synthesis with recurrent neural networks

Introduction New: Interactive demo using Google Colaboratory can be found here TTS-Cube is an end-2-end speech synthesis system that provides a full p

Tiberiu Boros 214 Dec 07, 2022
The NewSHead dataset is a multi-doc headline dataset used in NHNet for training a headline summarization model.

This repository contains the raw dataset used in NHNet [1] for the task of News Story Headline Generation. The code of data processing and training is available under Tensorflow Models - NHNet.

Google Research Datasets 31 Jul 15, 2022
Script to download some free japanese lessons in portuguse from NHK

Nihongo_nhk This is a script to download some free japanese lessons in portuguese from NHK. It can be executed by installing the packages with: pip in

Matheus Alves 2 Jan 06, 2022
Use Tensorflow2.7.0 Build OpenAI'GPT-2

TF2_GPT-2 Use Tensorflow2.7.0 Build OpenAI'GPT-2 使用最新tensorflow2.7.0构建openai官方的GPT-2 NLP模型 优点 使用无监督技术 拥有大量词汇量 可实现续写(堪比“xx梦续写”) 实现对话后续将应用于FloatTech的Bot

Watermelon 9 Sep 13, 2022
Code and dataset for the EMNLP 2021 Finding paper "Can NLI Models Verify QA Systems’ Predictions?"

Code and dataset for the EMNLP 2021 Finding paper "Can NLI Models Verify QA Systems’ Predictions?"

Jifan Chen 22 Oct 21, 2022
내부 작업용 django + vue(vuetify) boilerplate. 짠 하면 돌아감.

Pocket Galaxy 아주 간단한 개인용, 혹은 내부용 툴을 만들어야하는데 이왕이면 웹이 편하죠? 그럴때를 위해 만들어둔 django와 vue(vuetify)로 이뤄진 boilerplate 입니다. 각 폴더에 있는 설명서대로 실행을 시키면 일단 당장 뭔가가 돌아갑니

Jamie J. Seol 16 Dec 03, 2021
A PyTorch Implementation of End-to-End Models for Speech-to-Text

speech Speech is an open-source package to build end-to-end models for automatic speech recognition. Sequence-to-sequence models with attention, Conne

Awni Hannun 647 Dec 25, 2022
Develop open-source Python Arabic NLP libraries that the Arab world will easily use in all Natural Language Processing applications

Develop open-source Python Arabic NLP libraries that the Arab world will easily use in all Natural Language Processing applications

BADER ALABDAN 2 Oct 22, 2022
Application for shadowing Chinese.

chinese-shadowing Simple APP for shadowing chinese. With this application, it is very easy to record yourself, play the sound recorded and listen to s

Thomas Hirtz 5 Sep 06, 2022
The source code of HeCo

HeCo This repo is for source code of KDD 2021 paper "Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learning". Paper Link: htt

Nian Liu 106 Dec 27, 2022
A 30000+ Chinese MRC dataset - Delta Reading Comprehension Dataset

Delta Reading Comprehension Dataset 台達閱讀理解資料集 Delta Reading Comprehension Dataset (DRCD) 屬於通用領域繁體中文機器閱讀理解資料集。 本資料集期望成為適用於遷移學習之標準中文閱讀理解資料集。 本資料集從2,108篇

272 Dec 15, 2022
An implementation of WaveNet with fast generation

pytorch-wavenet This is an implementation of the WaveNet architecture, as described in the original paper. Features Automatic creation of a dataset (t

Vincent Herrmann 858 Dec 27, 2022
Converts text into a PDF of handwritten notes

Text To Handwritten Notes Converts text into a PDF of handwritten notes Explore the docs » · Report Bug · Request Feature · Steps: $ git clone https:/

UVSinghK 63 Oct 09, 2022
Implementation of Fast Transformer in Pytorch

Fast Transformer - Pytorch Implementation of Fast Transformer in Pytorch. This only work as an encoder. Yannic video AI Epiphany Install $ pip install

Phil Wang 167 Dec 27, 2022