ELSA-2: Extractive Linking of Summarization Approaches

Authors: Maksim Eremeev ([email protected]), Mars Wei-Lun Huang ([email protected]), Phoebe Chen ([email protected]), Anurag Illendula ([email protected])

This repo introduces an implementation of the ELSA hybrid summarization model. By using extractive attention masking mechanism, we combine large pre-trained transformer-based extractive and abstractive models, such as BART, PEGASUS, and BERTSum.

Datasets used for experiments

CNN-DailyMail: Link, original source: Link

XSum: Link, original source: Link

Downloading & Extracting datasets

wget https://s3.amazonaws.com/opennmt-models/Summary/cnndm.tar.gz
wget http://bollin.inf.ed.ac.uk/public/direct/XSUM-EMNLP18-Summary-Data-Original.tar.gz
wget https://www.dropbox.com/s/cmpfvzxdknkeal4/gazeta_jsonl.tar.gz

tar -xzf cnndm.tar.gz
tar -xzf XSUM-EMNLP18-Summary-Data-Original.tar.gz
tar -xzf gazeta_jsonl.tar.gz

Codestyle check

Before making a commmit / pull-request, please check the coding style by running the bash script in the codestyle directory. Make sure that your folder is included in codestyle/pycodestyle_files.txt list.

Your changes will not be approved if the script indicates any incongruities (this does not apply to 3rd-party code).

Usage:

cd codestyle
sh check_code_style.sh