There are 5 repositories under automatic-summarization topic.
Models to perform neural summarization (extractive and abstractive) using machine learning transformers and a tool to convert abstractive summarization datasets to the extractive task.
The purpose of this repository is to make prototypes as case study in the context of proof of concept(PoC) and research and development(R&D) that I have written in my website. The main research topics are Auto-Encoders in relation to the representation learning, the statistical machine learning for energy-based models, adversarial generation networks(GANs), Deep Reinforcement Learning such as Deep Q-Networks, semi-supervised learning, and neural network language model for natural language processing.
Machine learning models to automatically summarise scientific papers
微博自动摘要系统 Chinese Microblog Automatic Summary System
The Internet plays an increasingly important part in our daily lives as a source of written content for news and leisure. Yet it is tedious and difficult to sort through this staggering flow of information and stay updated with changes in our world, even using automated tools. Reading magazines and newspapers is too time-consuming, and there is a huge amount of online content that is updated or generated each minute. Our solution considers each user’s interests and leverages Artificial Intelligence, Machine Learning and Natural Language Processing in order to suggest to relevant articles from the internet.
A script to process the ArXiv-PubMed dataset.
Automatic summarisation of Medicines's Description
MOTS (MOdular Tool for Summarization) is a summarization system, written in Java. It is as modular as possible, and is intended to provide an architecture to implement and test new summarization methods, as well as to ease comparison with already implemented methods, in an unified framework.
LinTO's NLP service: Extractive Summarization
Content Summary Generator
using feature maximisation for summarizing scientifc documents
Data collection and resulting timelines for the paper Summarize Dates First: A Paradigm Shift in Timeline Summarization published at SIGIR 2021
Evaluation and agreement scripts for the DISCOSUMO project. Each evaluation script takes both manual annotations as automatic summarization output. The formatting of these files is highly project-specific. However, the evaluation functions for precision, recall, ROUGE, Jaccard, Cohen's kappa and Fleiss' kappa may be applicable to other domains too.
Code for paper 'Summary Refinement through Denoising'
MOTS (MOdular Tool for Summarization) is a summarization system, written in Java. It is as modular as possible, and is intended to provide an architecture to implement and test new summarization methods, as well as to ease comparison with already implemented methods, in an unified framework.
Google chrome extension which summarizes news web pages.
Автоматическое реферирование текста (TextRank, mBART)
Sample automatic summarization by flask python
Multidocument summarization using the SumBasic implementation
The repo contains resources from my Masters thesis