ELSA combines extractive and abstractive approaches to the automatic text summarization
-
Updated
Apr 6, 2021 - Python
ELSA combines extractive and abstractive approaches to the automatic text summarization
Scrapes, translates, summarizes, and scores news articles from El País via Hugging Face Helsinki, Google Pegasus, and BERT.
Bachelor's thesis on removing hate from online comments using paraphrasing: algorithm DPhate
A financial dashboard built using Streamlit, fine-tuned Transformers models and Prophet. Includes auto summarisation, sentiment analysis, and trend forecasting of stock and crypto news.
This repository contains the project of Natural Language Processing course at IIT Gandhinagar offered by Prof. Mayank Singh during Fall semester 2021-22. In this project an application to scrape stock related posts in real time and generate their summaries was developed.
Paragraph paraphrasing using the PEGASUS model from Google Research.
Amino Pegasus or AminoGasus for detect users in others community in Amino website
Transform images with text into a concise summary using Tesseract OCR and Google's Pegasus model
3rd Year: 1st - 104/100. Generative Modelling: Applying GANs to generate out-of-sample inter-class images - "The Mythical Pegasus: A Mysterious Journey".
Search platform for product manufacturers to learn "Consumer Insights"
[EMNLP 2023] FaMeSumm: Investigating and Improving Faithfulness of Medical Summarization. Support BART, PEGASUS, T5, mT5, BioBART, etc.
newsletter is a web-app that automatically generates newsletters and blog posts using Machine Learning
Codes for our paper "CTRLEval: An Unsupervised Reference-Free Metric for Evaluating Controlled Text Generation" (ACL 2022)
The Python-based web app extracts and summarizes news using NewsAPI, newspaper3k, spacy, Pegasus and T5 from Hugging Face. It categorizes news articles and uses a graph-based summary feature to summarize multiple documents. The app works with news in any language supported by NewsAPI.
The goal of this project is to design a classifier to use for sentiment analysis of product reviews. Our training set consists of reviews written by Amazon customers for various food products. The reviews, originally given on a 5 point scale, have been adjusted to a +1 or -1 scale, representing a positive or negative review, respectively.
Official implementation of the paper "IteraTeR: Understanding Iterative Revision from Human-Written Text" (ACL 2022)
Abstractive text summarization by fine-tuning seq2seq models.
Has been migrated to https://github.com/apache/incubator-pegasus/tree/master/python-client
Tencent Pre-training framework in PyTorch & Pre-trained Model Zoo
Add a description, image, and links to the pegasus topic page so that developers can more easily learn about it.
To associate your repository with the pegasus topic, visit your repo's landing page and select "manage topics."