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
Speech Recognition Database Management with python

Speech Recognition Database Management The main aim of this project is to recogn

Abhishek Kumar Jha 2 Feb 02, 2022
Sequence model architectures from scratch in PyTorch

This repository implements a variety of sequence model architectures from scratch in PyTorch. Effort has been put to make the code well structured so that it can serve as learning material. The train

Brando Koch 11 Mar 28, 2022
NAACL 2022: MCSE: Multimodal Contrastive Learning of Sentence Embeddings

MCSE: Multimodal Contrastive Learning of Sentence Embeddings This repository contains code and pre-trained models for our NAACL-2022 paper MCSE: Multi

Saarland University Spoken Language Systems Group 39 Nov 15, 2022
Simple text to phones converter for multiple languages

Phonemizer -- foʊnmaɪzɚ The phonemizer allows simple phonemization of words and texts in many languages. Provides both the phonemize command-line tool

CoML 762 Dec 29, 2022
Twitter Sentiment Analysis using #tag, words and username

Twitter Sentment Analysis Web App using #tag, words and username to fetch data finds Insides of data and Tells Sentiment of the perticular #tag, words or username.

Kumar Saksham 26 Dec 25, 2022
Poetry PEP 517 Build Backend & Core Utilities

Poetry Core A PEP 517 build backend implementation developed for Poetry. This project is intended to be a light weight, fully compliant, self-containe

Poetry 293 Jan 02, 2023
Skipgram Negative Sampling in PyTorch

PyTorch SGNS Word2Vec's SkipGramNegativeSampling in Python. Yet another but quite general negative sampling loss implemented in PyTorch. It can be use

Jamie J. Seol 287 Dec 14, 2022
【原神】自动演奏风物之诗琴的程序

疯物之诗琴 读取midi并自动演奏原神风物之诗琴。 可以自定义配置文件自动调整音符来适配风物之诗琴。 (原神1.4直播那天就开始做了!到现在才能放出来。。) 如何使用 在Release页面中下载打包好的程序和midi压缩包并解压。 双击运行“疯物之诗琴.exe”。 在原神中打开风物之诗琴,软件内输入

435 Jan 04, 2023
Auto translate textbox from Japanese to English or Indonesia

priconne-auto-translate Auto translate textbox from Japanese to English or Indonesia How to use Install python first, Anaconda is recommended Install

Aji Priyo Wibowo 5 Aug 25, 2022
Chinese real time voice cloning (VC) and Chinese text to speech (TTS).

Chinese real time voice cloning (VC) and Chinese text to speech (TTS). 好用的中文语音克隆兼中文语音合成系统,包含语音编码器、语音合成器、声码器和可视化模块。

Kuang Dada 6 Nov 08, 2022
Wikipedia-Utils: Preprocessing Wikipedia Texts for NLP

Wikipedia-Utils: Preprocessing Wikipedia Texts for NLP This repository maintains some utility scripts for retrieving and preprocessing Wikipedia text

Masatoshi Suzuki 44 Oct 19, 2022
This repository contains the codes for LipGAN. LipGAN was published as a part of the paper titled "Towards Automatic Face-to-Face Translation".

LipGAN Generate realistic talking faces for any human speech and face identity. [Paper] | [Project Page] | [Demonstration Video] Important Update: A n

Rudrabha Mukhopadhyay 438 Dec 31, 2022
Model parallel transformers in JAX and Haiku

Table of contents Mesh Transformer JAX Updates Pretrained Models GPT-J-6B Links Acknowledgments License Model Details Zero-Shot Evaluations Architectu

Ben Wang 4.9k Jan 04, 2023
Finally, some decent sample sentences

tts-dataset-prompts This repository aims to be a decent set of sentences for people looking to clone their own voices (e.g. using Tacotron 2). Each se

hecko 19 Dec 13, 2022
Knowledge Management for Humans using Machine Learning & Tags

HyperTag helps humans intuitively express how they think about their files using tags and machine learning. Represent how you think using tags. Find what you look for using semantic search for your t

Ravn Tech, Inc. 166 Jan 07, 2023
Machine learning models from Singapore's NLP research community

SG-NLP Machine learning models from Singapore's natural language processing (NLP) research community. sgnlp is a Python package that allows you to eas

AI Singapore | AI Makerspace 21 Dec 17, 2022
Code for the paper: Sequence-to-Sequence Learning with Latent Neural Grammars

Code for the paper: Sequence-to-Sequence Learning with Latent Neural Grammars

Yoon Kim 43 Dec 23, 2022
Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents

Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents [Project Page] [Paper] [Video] Wenlong Huang1, Pieter Abbee

Wenlong Huang 114 Dec 29, 2022
Finding Label and Model Errors in Perception Data With Learned Observation Assertions

Finding Label and Model Errors in Perception Data With Learned Observation Assertions This is the project page for Finding Label and Model Errors in P

Stanford Future Data Systems 17 Oct 14, 2022
DANeS is an open-source E-newspaper dataset by collaboration between DATASET JSC (dataset.vn) and AIV Group (aivgroup.vn)

DANeS - Open-source E-newspaper dataset Source: Technology vector created by macrovector - www.freepik.com. DANeS is an open-source E-newspaper datase

DATASET .JSC 64 Aug 17, 2022