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
Code release for "COTR: Correspondence Transformer for Matching Across Images"

COTR: Correspondence Transformer for Matching Across Images This repository contains the inference code for COTR. We plan to release the training code

UBC Computer Vision Group 358 Dec 24, 2022
Summarization module based on KoBART

KoBART-summarization Install KoBART pip install git+https://github.com/SKT-AI/KoBART#egg=kobart Requirements pytorch==1.7.0 transformers==4.0.0 pytor

seujung hwan, Jung 148 Dec 28, 2022
Easy-to-use CPM for Chinese text generation

CPM 项目描述 CPM(Chinese Pretrained Models)模型是北京智源人工智能研究院和清华大学发布的中文大规模预训练模型。官方发布了三种规模的模型,参数量分别为109M、334M、2.6B,用户需申请与通过审核,方可下载。 由于原项目需要考虑大模型的训练和使用,需要安装较为复杂

382 Jan 07, 2023
ByT5: Towards a token-free future with pre-trained byte-to-byte models

ByT5: Towards a token-free future with pre-trained byte-to-byte models ByT5 is a tokenizer-free extension of the mT5 model. Instead of using a subword

Google Research 409 Jan 06, 2023
ETM - R package for Topic Modelling in Embedding Spaces

ETM - R package for Topic Modelling in Embedding Spaces This repository contains an R package called topicmodels.etm which is an implementation of ETM

bnosac 37 Nov 06, 2022
A PyTorch-based model pruning toolkit for pre-trained language models

English | 中文说明 TextPruner是一个为预训练语言模型设计的模型裁剪工具包,通过轻量、快速的裁剪方法对模型进行结构化剪枝,从而实现压缩模型体积、提升模型速度。 其他相关资源: 知识蒸馏工具TextBrewer:https://github.com/airaria/TextBrewe

Ziqing Yang 231 Jan 08, 2023
Unifying Cross-Lingual Semantic Role Labeling with Heterogeneous Linguistic Resources (NAACL-2021).

Unifying Cross-Lingual Semantic Role Labeling with Heterogeneous Linguistic Resources Description This is the repository for the paper Unifying Cross-

Sapienza NLP group 16 Sep 09, 2022
An implementation of model parallel GPT-3-like models on GPUs, based on the DeepSpeed library. Designed to be able to train models in the hundreds of billions of parameters or larger.

GPT-NeoX An implementation of model parallel GPT-3-like models on GPUs, based on the DeepSpeed library. Designed to be able to train models in the hun

EleutherAI 3.1k Jan 08, 2023
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
Generate product descriptions, blogs, ads and more using GPT architecture with a single request to TextCortex API a.k.a Hemingwai

TextCortex - HemingwAI Generate product descriptions, blogs, ads and more using GPT architecture with a single request to TextCortex API a.k.a Hemingw

TextCortex AI 27 Nov 28, 2022
MHtyper is an end-to-end pipeline for recognized the Forensic microhaplotypes in Nanopore sequencing data.

MHtyper is an end-to-end pipeline for recognized the Forensic microhaplotypes in Nanopore sequencing data. It is implemented using Python.

willow 6 Jun 27, 2022
PyTorch Implementation of "Bridging Pre-trained Language Models and Hand-crafted Features for Unsupervised POS Tagging" (Findings of ACL 2022)

Feature_CRF_AE Feature_CRF_AE provides a implementation of Bridging Pre-trained Language Models and Hand-crafted Features for Unsupervised POS Tagging

Jacob Zhou 6 Apr 29, 2022
A Chinese to English Neural Model Translation Project

ZH-EN NMT Chinese to English Neural Machine Translation This project is inspired by Stanford's CS224N NMT Project Dataset used in this project: News C

Zhenbang Feng 29 Nov 26, 2022
Implementation of the Hybrid Perception Block and Dual-Pruned Self-Attention block from the ITTR paper for Image to Image Translation using Transformers

ITTR - Pytorch Implementation of the Hybrid Perception Block (HPB) and Dual-Pruned Self-Attention (DPSA) block from the ITTR paper for Image to Image

Phil Wang 17 Dec 23, 2022
Module for automatic summarization of text documents and HTML pages.

Automatic text summarizer Simple library and command line utility for extracting summary from HTML pages or plain texts. The package also contains sim

Mišo Belica 3k Jan 08, 2023
Scikit-learn style model finetuning for NLP

Scikit-learn style model finetuning for NLP Finetune is a library that allows users to leverage state-of-the-art pretrained NLP models for a wide vari

indico 665 Dec 17, 2022
Index different CKAN entities in Solr, not just datasets

ckanext-sitesearch Index different CKAN entities in Solr, not just datasets Requirements This extension requires CKAN 2.9 or higher and Python 3 Featu

Open Knowledge Foundation 3 Dec 02, 2022
Anuvada: Interpretable Models for NLP using PyTorch

Anuvada: Interpretable Models for NLP using PyTorch So, you want to know why your classifier arrived at a particular decision or why your flashy new d

EDGE 102 Oct 01, 2022
HF's ML for Audio study group

Hugging Face Machine Learning for Audio Study Group Welcome to the ML for Audio Study Group. Through a series of presentations, paper reading and disc

Vaibhav Srivastav 110 Jan 01, 2023
A library for finding knowledge neurons in pretrained transformer models.

knowledge-neurons An open source repository replicating the 2021 paper Knowledge Neurons in Pretrained Transformers by Dai et al., and extending the t

EleutherAI 96 Dec 21, 2022