Git Product home page Git Product logo

xai_binaryclassifier's Introduction

Dual-Classification of Scientific Paper Sentence

Code for KCC 2022 paper: Dual-Classification of Paper Sentence using Chunk Representation Method and Dependency Parsing

Setting up the code environment

$ virtualenv --python=python3.6 venv
$ source venv/bin/activate
$ pip install -r requirements.txt

All code only supports running on Linux.

Model Structure

Data

국내 논문 문장 의미 태깅 데이터셋

Directory and Pre-processing

의존 구문 분석 모델은 미공개(The dependency parser model is unpublished)

├── data
│   ├── origin.json
│   └── origin
│       ├──DP_origin_preprocess.json
│       └── merge_origin_preprocess
│           ├── origin_train.json
│           └── origin_test.json
├── bert
│   ├── init_weight
│   └── biaffine_model
│       └── multi
├── src
│   ├── dependency
│       └── merge.py
│   ├── functions
│       ├── biattention.py
│       ├── utils.py
│       ├── metric.py
│       └── processor.json
│   └── model
│       ├── main_functions_multi.py
│       └── model_multi.py
├── run_baseline_torch.py
├── requirements.txt
└── README.md
  • 원시 데이터(data/origin.json)를 의존 구문 분석 모델을 활용하여 입력 문장 쌍에 대한 어절 단위 의존 구문 구조 추출(data/origin/DP_origin_preprocess.json)

  • 입력 문장 쌍에 대한 어절 단위 의존 구문 구조(data/origin/DP_origin_preprocess.json)를 src/dependency/merge.py를 통해 입력 문장 쌍에 대한 청크 단위 의존 구문 구조로 변환(data/origin/merge_origin_preprocess/origin.json)

  • 학습 데이터와 평가 데이터를 세부분류별 4:1 비율로 나누기(data/origin/merge_origin_preprocess/origin_train.json, data/origin/merge_origin_preprocess/origin_test.json)

  • bert/init_weight의 vocab.json에 청크 단위로 구분해주는 스폐셜 토큰(Special Token) <WORD> 추가

Train & Test

Pretrained model

  • KLUE/BERT-base

How To Run

python run_baseline_torch.py

Results

Model Macro F1 Acc
BERT 89.66% 89.90%
proposed 89.75% 89.99%

xai_binaryclassifier's People

Contributors

kellykim1110 avatar kunlp avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.