SummVis is an interactive visualization tool for text summarization.

Overview

SummVis

SummVis is an interactive visualization tool for analyzing abstractive summarization model outputs and datasets.

Figure

Installation

IMPORTANT: Please use python>=3.8 since some dependencies require that for installation.

git clone https://github.com/robustness-gym/summvis.git
cd summvis
pip install -r requirements.txt
python -m spacy download en_core_web_sm

Quickstart

Follow the steps below to start using SummVis immediately.

1. Download and extract data

Download our pre-cached dataset that contains predictions for state-of-the-art models such as PEGASUS and BART on 1000 examples taken from the CNN / Daily Mail validation set.

mkdir data
mkdir preprocessing
curl https://storage.googleapis.com/sfr-summvis-data-research/cnn_dailymail_1000.validation.anonymized.zip --output preprocessing/cnn_dailymail_1000.validation.anonymized.zip
unzip preprocessing/cnn_dailymail_1000.validation.anonymized.zip -d preprocessing/

2. Deanonymize data

Next, we'll need to add the original examples from the CNN / Daily Mail dataset to deanonymize the data (this information is omitted for copyright reasons). The preprocessing.py script can be used for this with the --deanonymize flag.

Deanonymize 10 examples (try_it mode):

python preprocessing.py \
--deanonymize \
--dataset_rg preprocessing/cnn_dailymail_1000.validation.anonymized \
--dataset cnn_dailymail \
--version 3.0.0 \
--split validation \
--processed_dataset_path data/try:cnn_dailymail_1000.validation \
--try_it

This will take between 10 seconds and several minutes depending on whether you've previously loaded CNN/DailyMail from the Datasets library.

3. Run SummVis

Finally, we're ready to run the Streamlit app. Once the app loads, make sure it's pointing to the right File at the top of the interface.

streamlit run summvis.py

General instructions for running with pre-loaded datasets

1. Download one of the pre-loaded datasets:

CNN / Daily Mail (1000 examples from validation set): https://storage.googleapis.com/sfr-summvis-data-research/cnn_dailymail_1000.validation.anonymized.zip
CNN / Daily Mail (full validation set): https://storage.googleapis.com/sfr-summvis-data-research/cnn_dailymail.validation.anonymized.zip
XSum (1000 examples from validation set): https://storage.googleapis.com/sfr-summvis-data-research/xsum_1000.validation.anonymized.zip
XSum (full validation set): https://storage.googleapis.com/sfr-summvis-data-research/xsum.validation.anonymized.zip

We recommend that you choose the smallest dataset that fits your need in order to minimize download / preprocessing time.

Example: Download and unzip CNN / Daily Mail

mkdir data
mkdir preprocessing
curl https://storage.googleapis.com/sfr-summvis-data-research/cnn_dailymail_1000.validation.anonymized.zip --output preprocessing/cnn_dailymail_1000.validation.anonymized.zip
unzip preprocessing/cnn_dailymail_1000.validation.anonymized.zip -d preprocessing/

2. Deanonymize n examples:

Set the --n_samples argument and name the --processed_dataset_path output file accordingly.

Example: Deanonymize 100 examples from CNN / Daily Mail:

python preprocessing.py \
--deanonymize \
--dataset_rg preprocessing/cnn_dailymail_1000.validation.anonymized \
--dataset cnn_dailymail \
--version 3.0.0 \
--split validation \
--processed_dataset_path data/100:cnn_dailymail_1000.validation \
--n_samples 100

Example: Deanonymize all pre-loaded examples from CNN / Daily Mail (1000 examples dataset):

python preprocessing.py \
--deanonymize \
--dataset_rg preprocessing/cnn_dailymail_1000.validation.anonymized \
--dataset cnn_dailymail \
--version 3.0.0 \
--split validation \
--processed_dataset_path data/full:cnn_dailymail_1000.validation \
--n_samples 1000

Example: Deanonymize all pre-loaded examples from CNN / Daily Mail (full dataset):

python preprocessing.py \
--deanonymize \
--dataset_rg preprocessing/cnn_dailymail.validation.anonymized \
--dataset cnn_dailymail \
--version 3.0.0 \
--split validation \
--processed_dataset_path data/full:cnn_dailymail.validation

Example: Deanonymize all pre-loaded examples from XSum (1000 examples dataset):

python preprocessing.py \
--deanonymize \
--dataset_rg preprocessing/xsum_1000.validation.anonymized \
--dataset xsum \
--split validation \
--processed_dataset_path data/full:xsum_1000.validation \
--n_samples 1000

3. Run SummVis

Once the app loads, make sure it's pointing to the right File at the top of the interface.

streamlit run summvis.py

Alternately, if you need to point SummVis to a folder where your data is stored.

streamlit run summvis.py -- --path your/path/to/data

Note that the additional -- is not a mistake, and is required to pass command-line arguments in streamlit.

Get your data into SummVis: end-to-end preprocessing

You can also perform preprocessing end-to-end to load any summarization dataset or model predictions into SummVis. Instructions for this are provided below.

Prior to running the following, an additional install step is required:

python -m spacy download en_core_web_lg

1. Standardize and save dataset to disk.

Loads in a dataset from HF, or any dataset that you have and stores it in a standardized format with columns for document and summary:reference.

Example: Save CNN / Daily Mail validation split to disk as a jsonl file.

python preprocessing.py \
--standardize \
--dataset cnn_dailymail \
--version 3.0.0 \
--split validation \
--save_jsonl_path preprocessing/cnn_dailymail.validation.jsonl

Example: Load custom my_dataset.jsonl, standardize, and save.

python preprocessing.py \
--standardize \
--dataset_jsonl path/to/my_dataset.jsonl \
--doc_column name_of_document_column \
--reference_column name_of_reference_summary_column \
--save_jsonl_path preprocessing/my_dataset.jsonl

2. Add predictions to the saved dataset.

Takes a saved dataset that has already been standardized and adds predictions to it from prediction jsonl files. Cached predictions for several models available here: https://storage.googleapis.com/sfr-summvis-data-research/predictions.zip

You may also generate your own predictions using this this script.

Example: Add 6 prediction files for PEGASUS and BART to the dataset.

python preprocessing.py \
--join_predictions \
--dataset_jsonl preprocessing/cnn_dailymail.validation.jsonl \
--prediction_jsonls \
predictions/bart-cnndm.cnndm.validation.results.anonymized \
predictions/bart-xsum.cnndm.validation.results.anonymized \
predictions/pegasus-cnndm.cnndm.validation.results.anonymized \
predictions/pegasus-multinews.cnndm.validation.results.anonymized \
predictions/pegasus-newsroom.cnndm.validation.results.anonymized \
predictions/pegasus-xsum.cnndm.validation.results.anonymized \
--save_jsonl_path preprocessing/cnn_dailymail.validation.jsonl

3. Run the preprocessing workflow and save the dataset.

Takes a saved dataset that has been standardized, and predictions already added. Applies all the preprocessing steps to it (running spaCy, lexical and semantic aligners), and stores the processed dataset back to disk.

Example: Autorun with default settings on a few examples to try it.

python preprocessing.py \
--workflow \
--dataset_jsonl preprocessing/cnn_dailymail.validation.jsonl \
--processed_dataset_path data/cnn_dailymail.validation \
--try_it

Example: Autorun with default settings on all examples.

python preprocessing.py \
--workflow \
--dataset_jsonl preprocessing/cnn_dailymail.validation.jsonl \
--processed_dataset_path data/cnn_dailymail

Citation

When referencing this repository, please cite this paper:

@misc{vig2021summvis,
      title={SummVis: Interactive Visual Analysis of Models, Data, and Evaluation for Text Summarization}, 
      author={Jesse Vig and Wojciech Kryscinski and Karan Goel and Nazneen Fatema Rajani},
      year={2021},
      eprint={2104.07605},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2104.07605}
}

Acknowledgements

We thank Michael Correll for his valuable feedback.

Owner
Robustness Gym
Building tools for evaluating and repairing ML models.
Robustness Gym
High performance, editable, stylable datagrids in jupyter and jupyterlab

An ipywidgets wrapper of regular-table for Jupyter. Examples Two Billion Rows Notebook Click Events Notebook Edit Events Notebook Styling Notebook Pan

J.P. Morgan Chase 75 Dec 15, 2022
Visualization of the World Religion Data dataset by Correlates of War Project.

World Religion Data Visualization Visualization of the World Religion Data dataset by Correlates of War Project. Mostly personal project to famirializ

Emile Bangma 1 Oct 15, 2022
DALLE-tools provided useful dataset utilities to improve you workflow with WebDatasets.

DALLE tools DALLE-tools is a github repository with useful tools to categorize, annotate or check the sanity of your datasets. Installation Just clone

11 Dec 25, 2022
在原神中使用围栏绘图

yuanshen_draw 在原神中使用围栏绘图 文件说明 toLines.py 将一张图片转换为对应的线条集合,视频可以按帧转换。 draw.py 在原神家园里绘制一张线条图。 draw_video.py 在原神家园里绘制视频(自动按帧摆放,截图(win)并回收) cat_to_video.py

14 Oct 08, 2022
Python ts2vg package provides high-performance algorithm implementations to build visibility graphs from time series data.

ts2vg: Time series to visibility graphs The Python ts2vg package provides high-performance algorithm implementations to build visibility graphs from t

Carlos Bergillos 26 Dec 17, 2022
Automatically generate GitHub activity!

Commit Bot Automatically generate GitHub activity! We've all wanted to be the developer that commits every day, but that requires a lot of work. Let's

Ricky 4 Jun 07, 2022
Design your own matplotlib stylefile interactively

Tired of playing with font sizes and other matplotlib parameters every time you start a new project or write a new plotting function? Want all you plots have the same style? Use matplotlib configurat

yobi byte 207 Dec 08, 2022
Functions for easily making publication-quality figures with matplotlib.

Data-viz utils 📈 Functions for data visualization in matplotlib 📚 API Can be installed using pip install dvu and then imported with import dvu. You

Chandan Singh 16 Sep 15, 2022
Automatic data visualization in atom with the nteract data-explorer

Data Explorer Interactively explore your data directly in atom with hydrogen! The nteract data-explorer provides automatic data visualization, so you

Ben Russert 65 Dec 01, 2022
Interactive Dashboard for Visualizing OSM Data Change

Dashboard and intuitive data downloader for more interactive experience with interpreting osm change data.

1 Feb 20, 2022
Python Package for CanvasXpress JS Visualization Tools

CanvasXpress Python Library About CanvasXpress for Python CanvasXpress was developed as the core visualization component for bioinformatics and system

Dr. Todd C. Brett 5 Nov 07, 2022
The Spectral Diagram (SD) is a new tool for the comparison of time series in the frequency domain

The Spectral Diagram (SD) is a new tool for the comparison of time series in the frequency domain. The SD provides a novel way to display the coherence function, power, amplitude, phase, and skill sc

Mabel 3 Oct 10, 2022
Plotting data from the landroid and a raspberry pi zero to a influx-db

landroid-pi-influx Plotting data from the landroid and a raspberry pi zero to a influx-db Dependancies Hardware: Landroid WR130E Raspberry Pi Zero Wif

2 Oct 22, 2021
Gallery of applications built using bqplot and widget libraries like ipywidgets, ipydatagrid etc.

bqplot Gallery This is a gallery of bqplot examples. View the gallery at https://bqplot.github.io/bqplot-gallery. Contributing new examples Clone this

8 Aug 23, 2022
Pglive - Pglive package adds support for thread-safe live plotting to pyqtgraph

Live pyqtgraph plot Pglive package adds support for thread-safe live plotting to

Martin Domaracký 15 Dec 10, 2022
Manim is an animation engine for explanatory math videos.

A community-maintained Python framework for creating mathematical animations.

12.4k Dec 30, 2022
A small tool to test and visualize protein embeddings and amino acid proportions.

polyprotein_stats A small tool to test and visualize protein embeddings and amino acid proportions. Currently deployed on streamlit.io. Given a set of

2 Jan 07, 2023
Data Visualizations for the #30DayChartChallenge

The #30DayChartChallenge This repository contains all the charts made for the #30DayChartChallenge during the month of April. This project aims to exp

Isaac Arroyo 7 Sep 20, 2022
A Scheil-Gulliver simulation tool using pycalphad.

scheil A Scheil-Gulliver simulation tool using pycalphad. import matplotlib.pyplot as plt from pycalphad import Database, variables as v from scheil i

pycalphad 6 Dec 10, 2021
A concise grammar of interactive graphics, built on Vega.

Vega-Lite Vega-Lite provides a higher-level grammar for visual analysis that generates complete Vega specifications. You can find more details, docume

Vega 4k Jan 08, 2023