bart

Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo

LightSeq: A High Performance Library for Sequence Processing and Generation

Self-contained Machine Learning and Natural Language Processing library in Go

Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)

TextBox is an open-source library for building text generation system.

Build and train state-of-the-art natural language processing models using BERT

Code associated with the "Data Augmentation using Pre-trained Transformer Models" paper

A tool to automatically summarize documents abstractively using the BART or PreSumm Machine Learning Model.

Pytorch implementation of baseline models of KQA Pro, a large-scale dataset of complex question answering over knowledge base.

Code associated with the "Data Augmentation using Pre-trained Transformer Models" paper

Question Generator with Transformer models

The French summarization dataset introduced in "BARThez: a Skilled Pretrained French Sequence-to-Sequence Model".

BART fare reduction

Comparing state of the art models for text summary generation

Uses Stan sampler and math library to semiparametrically fit linear and multilevel models with additive Bayesian Additive Regression Tree (BART) components.

BART JSON API using Node and Express.

Fine-tuning BART on COVID Dialogue Dataset

The BART app for commuters, now native on iOS

Sample Bixby Capsule - BART Schedule

A visualization tool for the BART API, that shows delays as 'traffic'.

Code for the Paper 'Summaformers @ LaySumm 20, LongSumm 20' at EMNLP 2020, Scholarly Document Processing Workshop

Implementation and helper scripts for the BART-TL model - https://www.aclweb.org/anthology/2021.eacl-main.121/

Evaluating BART and Synthetic Tree-Based Methods for the Estimation of Individual Causal Effects, final project for CM764 - Statistical Learning - Function Estimation at uWaterloo

The main problem of conditional text generation is that it is mainly based on the content of an input set of examples: this leads to little diversification of the generated text. To overcome this shortcoming, we have fine tuned CTRL using three different datasets. The first model has been used as a baseline for comparison, while the other two have been used to obtain more formal and informal text. The BART model has been employed for text classification to gauge formality.

Codes for our paper "JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs" (ACL 2021 Findings)

Shiny app for displaying BART hourly origin-destination data.

Text summarization refers to the technique of shortening long pieces of text. The intention is to create a coherent and fluent summary having only the main points outlined in the document. Automatic text summarization is a common problem in machine learning and natural language processing (NLP).Text summarization is the problem of creating a short, accurate, and fluent summary of a longer text document. Automatic text summarization methods are greatly needed to address the ever-growing amount of text data available online to both better help discover relevant information and to consume relevant information faster.

Auto summarization from BPE tokenization

An open source beautiful and powerful android app for BART