Korean extractive summarization. 2021 AI 텍스트 요약 온라인 해커톤 화성갈끄니까팀 코드

Overview

korean extractive summarization

2021 AI 텍스트 요약 온라인 해커톤 화성갈끄니까팀 코드

Leaderboard

1

Notice

  • Text Summarization with Pretrained Encoders에 나오는 bertsumext모델(extractive summarization을 위해 bert위에 추가적으로 inter-sentence 레이어를 얹은구조)의 bert를 klue/roberta-large모델로 대체하여 구성하였음.
  • uoneway님 KoBertSum 레포지토리를 기반으로 만들어짐.
  • 수정된 부분 - pytorch 1.1 ->pytorch 1.7.1버전 지원하도록 수정.
  • 수정된 부분 - transformers 4.0 버전 지원하도록 수정, klue/roberta-large 포팅
  • 수정된 부분 - 불필요한 부분 삭제 or 수정

Process

  1. Environment Setting
pip install -r requirements.txt
python src/others/install_mecab.py # mecab설치
  1. Preprocess( ./ext/data/raw/train.jsonl, ./ext/data/raw/test.jsonl이 있어야 함)
python main.py -task make_data -n_cpus 5
  1. Train
python main.py -task train -target_summary_sent abs -visible_gpus 0
  1. Validation(path에 있는 모델파일 전부 validation하는 코드임.)
python main.py -task valid -model_path 1209_1236
  1. Test and submission 파일 생성
python main.py -task test -test_from 1209_1236/model_step_500.pt -visible_gpus 0
cd ext/results/
python get_submission.py -filename result_1209_1236_step_500.candidate.jsonl

포함되지 않은 부분

  • 대회에선, ensemble 이용해서 rouge-L 53.15 -> 53.5 으로 끌어올렸는데, 간단하니까 필요하신 분들은 구현해서 사용하시면 성능향상에 도움이 될 듯.

  • 추가로 데이터셋 폼(jsonl각 line)은 이렇게 구성됨(세줄요약 데이터셋)

{"category": "none", "id": 0, "article_original": ["","","","",""], "extractive": [2, 3, 4], "abstractive": "", "extractive_sents": ["", "", ""]}

Reference

Owner
NLP, ML research
Converts python code into c++ by using OpenAI CODEX.

🦾 codex_py2cpp 🤖 OpenAI Codex Python to C++ Code Generator Your Python Code is too slow? 🐌 You want to speed it up but forgot how to code in C++? ⌨

Alexander 423 Jan 01, 2023
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
Code for text augmentation method leveraging large-scale language models

HyperMix Code for our paper GPT3Mix and conducting classification experiments using GPT-3 prompt-based data augmentation. Getting Started Installing P

NAVER AI 47 Dec 20, 2022
A list of NLP(Natural Language Processing) tutorials built on Tensorflow 2.0.

A list of NLP(Natural Language Processing) tutorials built on Tensorflow 2.0.

Won Joon Yoo 335 Jan 04, 2023
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
Deep Learning Topics with Computer Vision & NLP

Deep learning Udacity Course Deep Learning Topics with Computer Vision & NLP for the AWS Machine Learning Engineer Nanodegree Program Tasks are mostly

Simona Mircheva 1 Jan 20, 2022
Comprehensive-E2E-TTS - PyTorch Implementation

A Non-Autoregressive End-to-End Text-to-Speech (text-to-wav), supporting a family of SOTA unsupervised duration modelings. This project grows with the research community, aiming to achieve the ultima

Keon Lee 114 Nov 13, 2022
Ask for weather information like a human

weather-nlp About Ask for weather information like a human. Goals Understand typical questions like: Hourly temperatures in Potsdam on 2020-09-15. Rai

5 Oct 29, 2022
DeBERTa: Decoding-enhanced BERT with Disentangled Attention

DeBERTa: Decoding-enhanced BERT with Disentangled Attention This repository is the official implementation of DeBERTa: Decoding-enhanced BERT with Dis

Microsoft 1.2k Jan 03, 2023
Implementation of "Adversarial purification with Score-based generative models", ICML 2021

Adversarial Purification with Score-based Generative Models by Jongmin Yoon, Sung Ju Hwang, Juho Lee This repository includes the official PyTorch imp

15 Dec 15, 2022
An IVR Chatbot which can exponentially reduce the burden of companies as well as can improve the consumer/end user experience.

IVR-Chatbot Achievements 🏆 Team Uhtred won the Maverick 2.0 Bot-a-thon 2021 organized by AbInbev India. ❓ Problem Statement As we all know that, lot

ARYAMAAN PANDEY 9 Dec 08, 2022
Analyse japanese ebooks using MeCab to determine the difficulty level for japanese learners

japanese-ebook-analysis This aim of this project is to make analysing the contents of a japanese ebook easy and streamline the process for non-technic

Christoffer Aakre 14 Jul 23, 2022
Code for "Generative adversarial networks for reconstructing natural images from brain activity".

Reconstruct handwritten characters from brains using GANs Example code for the paper "Generative adversarial networks for reconstructing natural image

K. Seeliger 2 May 17, 2022
☀️ Measuring the accuracy of BBC weather forecasts in Honolulu, USA

Accuracy of BBC Weather forecasts for Honolulu This repository records the forecasts made by BBC Weather for the city of Honolulu, USA. Essentially, t

Max Halford 12 Oct 15, 2022
Tool to add main subject to items on Wikidata using a WMFs CirrusSearch for named entity recognition or a manually supplied list of QIDs

ItemSubjector Tool made to add main subject statements to items based on the title using a home-brewed CirrusSearch-based Named Entity Recognition alg

Dennis Priskorn 9 Nov 17, 2022
OpenChat: Opensource chatting framework for generative models

OpenChat is opensource chatting framework for generative models.

Hyunwoong Ko 427 Jan 06, 2023
A full spaCy pipeline and models for scientific/biomedical documents.

This repository contains custom pipes and models related to using spaCy for scientific documents. In particular, there is a custom tokenizer that adds

AI2 1.3k Jan 03, 2023
TruthfulQA: Measuring How Models Imitate Human Falsehoods

TruthfulQA: Measuring How Models Imitate Human Falsehoods

69 Dec 25, 2022
This repository contains Python scripts for extracting linguistic features from Filipino texts.

Filipino Text Linguistic Feature Extractors This repository contains scripts for extracting linguistic features from Filipino texts. The scripts were

Joseph Imperial 1 Oct 05, 2021
Finetune gpt-2 in google colab

gpt-2-colab finetune gpt-2 in google colab sample result (117M) from retraining on A Tale of Two Cities by Charles Di

212 Jan 02, 2023