Diaformer: Automatic Diagnosis via Symptoms Sequence Generation

Overview

Diaformer

Diaformer: Automatic Diagnosis via Symptoms Sequence Generation (AAAI 2022)

Diaformer is an efficient model for automatic diagnosis via symptoms sequence generation. It takes the sequence of symptoms as input, and predicts the inquiry symptoms in the way of sequence generation.

Figure 1: Illustration of symptom attention framework.

Requirements

Our experiments are conducted on Python 3.8 and Pytorch == 1.8.0. The main requirements are:

  • transformers==2.1.1
  • torch
  • numpy
  • tqdm
  • sklearn
  • keras
  • boto3

In the root directory, run following command to install the required libraries.

pip install -r requirement.txt

Usage

  1. Download data

    Download the datasets, then decompress them and put them in the corrsponding documents in \data. For example, put the data of Synthetic Dataset under data/synthetic_dataset.

    The dataset can be downloaded as following links:

  2. Build data

    Switch to the corresponding directory of the dataset and just run preprocess.py to preprocess data and generate a vocabulary of symptoms.

  3. Train and test

    Train and test models by the follow commands.

    Diaformer

    # Train and test on Diaformer
    # Run on MuZhi dataset
    python Diaformer.py --dataset_path data/muzhi_dataset --batch_size 16 --lr 5e-5 --min_probability 0.009 --max_turn 20 --start_test 10 
    
    # Run on Dxy dataset
    python Diaformer.py --dataset_path data/dxy_dataset --batch_size 16 --lr 5e-5 --min_probability 0.012 --max_turn 20 --start_test 10 
    
    # Run on Synthetic dataset
    python Diaformer.py --dataset_path data/synthetic_dataset --batch_size 16 --lr 5e-5 --min_probability 0.01 --max_turn 20 --start_test 10

    Diaformer_GPT2

    # Train and test on GPT2 variant of Diaformer
    python GPT2_variant.py --dataset_path data/synthetic_dataset --batch_size 16 --lr 5e-5 --min_probability 0.01 --max_turn 20 --start_test 10

    Diaformer_UniLM

    # Train and test on UniLM variant of Diaformer
    python UniLM_variant.py --dataset_path data/synthetic_dataset --batch_size 16 --lr 5e-5 --min_probability 0.01 --max_turn 20 --start_test 10

    Ablation study

    # run ablation study
    # w/o Sequence Shuffle
    python Diaformer.py --dataset_path data/synthetic_dataset --batch_size 16 --lr 5e-5 --min_probability 0.01 --max_turn 20 --start_test 10 --no_sequence_shuffle
    
    # w/o Synchronous Learning
    python Diaformer.py --dataset_path data/synthetic_dataset --batch_size 16 --lr 5e-5 --min_probability 0.01 --max_turn 20 --start_test 10 --no_synchronous_learning
    
    # w/o Repeated Sequence
    python Diaformer.py --dataset_path data/synthetic_dataset --batch_size 16 --lr 5e-5 --min_probability 0.01 --max_turn 20 --start_test 10 --no_repeated_sequence

    Generative inference

    # save the model
    python Diaformer.py --dataset_path data/synthetic_dataset --batch_size 16 --lr 5e-5 --min_probability 0.01 --max_turn 20 --start_test 10 --model_output_path models
    # use the trained model to output the results
    python predict.py --dataset_path data/synthetic_dataset --min_probability 0.01 --max_turn 20 --pretrained_model models/ --result_output_path results.json
Owner
Junying Chen
Junying Chen
Refactored version of FastSpeech2

Refactored version of FastSpeech2. An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"

ILJI CHOI 10 May 26, 2022
PyTorch implementation of NATSpeech: A Non-Autoregressive Text-to-Speech Framework

A Non-Autoregressive Text-to-Speech (NAR-TTS) framework, including official PyTorch implementation of PortaSpeech (NeurIPS 2021) and DiffSpeech (AAAI 2022)

760 Jan 03, 2023
Simple and efficient RevNet-Library with DeepSpeed support

RevLib Simple and efficient RevNet-Library with DeepSpeed support Features Half the constant memory usage and faster than RevNet libraries Less memory

Lucas Nestler 112 Dec 05, 2022
It analyze the sentiment of the user, whether it is postive or negative.

Sentiment-Analyzer-Tool It analyze the sentiment of the user, whether it is postive or negative. It uses streamlit library for creating this sentiment

Paras Patidar 18 Dec 17, 2022
novel deep learning research works with PaddlePaddle

Research 发布基于飞桨的前沿研究工作,包括CV、NLP、KG、STDM等领域的顶会论文和比赛冠军模型。 目录 计算机视觉(Computer Vision) 自然语言处理(Natrual Language Processing) 知识图谱(Knowledge Graph) 时空数据挖掘(Spa

1.5k Jan 03, 2023
Code to reproduce the results of the paper 'Towards Realistic Few-Shot Relation Extraction' (EMNLP 2021)

Realistic Few-Shot Relation Extraction This repository contains code to reproduce the results in the paper "Towards Realistic Few-Shot Relation Extrac

Bloomberg 8 Nov 09, 2022
ChessCoach is a neural network-based chess engine capable of natural-language commentary.

ChessCoach is a neural network-based chess engine capable of natural-language commentary.

Chris Butner 380 Dec 03, 2022
The ability of computer software to identify words and phrases in spoken language and convert them to human-readable text

speech-recognition-py Speech recognition is the ability of computer software to identify words and phrases in spoken language and convert them to huma

Deepangshi 1 Apr 03, 2022
Ecommerce product title recognition package

revizor This package solves task of splitting product title string into components, like type, brand, model and article (or SKU or product code or you

Bureaucratic Labs 16 Mar 03, 2022
Crie tokens de autenticação íntegros e seguros com UToken.

UToken - Tokens seguros. UToken (ou Unhandleable Token) é uma bilioteca criada para ser utilizada na geração de tokens seguros e íntegros, ou seja, nã

Jaedson Silva 0 Nov 29, 2022
Linear programming solver for paper-reviewer matching and mind-matching

Paper-Reviewer Matcher A python package for paper-reviewer matching algorithm based on topic modeling and linear programming. The algorithm is impleme

Titipat Achakulvisut 66 Jul 05, 2022
Blackstone is a spaCy model and library for processing long-form, unstructured legal text

Blackstone Blackstone is a spaCy model and library for processing long-form, unstructured legal text. Blackstone is an experimental research project f

ICLR&D 579 Jan 08, 2023
🕹 An esoteric language designed so that the program looks like the transcript of a Pokémon battle

PokéBattle is an esoteric language designed so that the program looks like the transcript of a Pokémon battle. Original inspiration and specification

Eduardo Correia 9 Jan 11, 2022
Topic Modelling for Humans

gensim – Topic Modelling in Python Gensim is a Python library for topic modelling, document indexing and similarity retrieval with large corpora. Targ

RARE Technologies 13.8k Jan 02, 2023
A demo for end-to-end English and Chinese text spotting using ABCNet.

ABCNet_Chinese A demo for end-to-end English and Chinese text spotting using ABCNet. This is an old model that was trained a long ago, which serves as

Yuliang Liu 45 Oct 04, 2022
LSTC: Boosting Atomic Action Detection with Long-Short-Term Context

LSTC: Boosting Atomic Action Detection with Long-Short-Term Context This Repository contains the code on AVA of our ACM MM 2021 paper: LSTC: Boosting

Tencent YouTu Research 9 Oct 11, 2022
초성 해석기 based on ko-BART

초성 해석기 개요 한국어 초성만으로 이루어진 문장을 입력하면, 완성된 문장을 예측하는 초성 해석기입니다. 초성: ㄴㄴ ㄴㄹ ㅈㅇㅎ 예측 문장: 나는 너를 좋아해 모델 모델은 SKT-AI에서 공개한 Ko-BART를 이용합니다. 데이터 문장 단위로 이루어진 아무 코퍼스나

Dawoon Jung 29 Oct 28, 2022
Chatbot with Pytorch, Python & Nextjs

Installation Instructions Make sure that you have Python 3, gcc, venv, and pip installed. Clone the repository $ git clone https://github.com/sahr

Rohit Sah 0 Dec 11, 2022
用Resnet101+GPT搭建一个玩王者荣耀的AI

基于pytorch框架用resnet101加GPT搭建AI玩王者荣耀 本源码模型主要用了SamLynnEvans Transformer 的源码的解码部分。以及pytorch自带的预训练模型"resnet101-5d3b4d8f.pth"

冯泉荔 2.2k Jan 03, 2023
PyABSA - Open & Efficient for Framework for Aspect-based Sentiment Analysis

PyABSA - Open & Efficient for Framework for Aspect-based Sentiment Analysis

YangHeng 567 Jan 07, 2023