Abstractive BERT-based Text Summarizer

A BERT-based summarizer, centered towards a simple API: some text in, a summary out, both strings. Also at pypi.org as package sumbert.

Installation:

pip3 install sumbert

or if you want ot play with the code, after cloning this, and going into the resulting folder, install as an editable package with:

pip3 install -e .

Usage:

$ python3 -i
>>> from sumbert import summarize
>>> 
>>> text= """... your favorite story ..."""
>>> print(summarize(text))

This package is designed as a simple API for an otherwise fairy intricate set of components.

Credits:

The code is derived from the bertabs submodule in the HuggingFace transformers package at

https://github.com/huggingface/transformers

which credits the abstractive summarization described in the article Text Summarization with Pretrained Encoders by Yang Liu and Mirella Lapata.

The original code described in the article can be found on the Yang Liu's github repository.

Metadata

Release files for sumbert 1.0.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for sumbert 1.0.0
File	Size	Uploaded	Provenance	Actions
sumbert-1.0.0.tar.gz	16.5 kB	Apr 3, 2020	Without provenance	Details for sumbert-1.0.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for sumbert 1.0.0
File	Interpreter	ABI	Platform	Actions Reset
sumbert-1.0.0-py3-none-any.whl 21.5 kB Apr 3, 2020 Without provenance	Python 3	none	any	Details for sumbert-1.0.0-py3-none-any.whl

Total release size: 38.0 kB

Release files / sumbert-1.0.0.tar.gz

Download URL	sumbert-1.0.0.tar.gz
Size	16.5 kB
Tags	Source
SHA-256 checksum How to use checksums	`76df4cd35b644ce1161617ae9d5d89a01321cd3b0707526d59702f0b57a7aefc`
BLAKE2b-256 checksum How to use checksums	`3c384ac232db7fd2a6c3956a7a3316147e205256f508693b2730c954f8b7309d`
Upload date	Apr 3, 2020
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.1.1 pkginfo/1.5.0.1 requests/2.21.0 setuptools/42.0.0 requests-toolbelt/0.9.1 tqdm/4.32.2 CPython/3.7.4`

Release files / sumbert-1.0.0-py3-none-any.whl

Download URL	sumbert-1.0.0-py3-none-any.whl
Size	21.5 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`0031a7d06f4af9b0c1ef75d73152d1aa6e5bca5bf66c2b425d34204fd4dcaffd`
BLAKE2b-256 checksum How to use checksums	`91373f7817796ea9a7d3c7f31b171ee4e27ca0f1463e13d99d195cf2caf37b26`
Upload date	Apr 3, 2020
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.1.1 pkginfo/1.5.0.1 requests/2.21.0 setuptools/42.0.0 requests-toolbelt/0.9.1 tqdm/4.32.2 CPython/3.7.4`

Security for sumbert 1.0.0

Report project as malware

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

1.0.0 This release

Apr 3, 2020 2 release files No provenance

sumbert 1.0.0