Python implimentation of TextRank for text document NLP parsing and summarization
Project description
Python implementation of TextRank, based on the Mihalcea 2004 paper.
Modifications to the original algorithm by Rada Mihalcea, et al. include:
fixed bug; see Java impl, 2008
use of lemmatization instead of stemming
verbs included in the graph (but not in the resulting keyphrases)
named entity recognition
normalized keyphrase ranks used in summarization
The results produced by this implementation are intended more for use as feature vectors in machine learning, not as academic paper summaries.
Inspired by Williams 2016 talk on text summarization.
Example Usage
See PyTextRank wiki
Dependencies and Installation
This code has dependencies on several other Python projects:
To install from PyPi:
pip install pytextrank
To install from this Git repo:
pip install -r requirements.txt
After installation you need to download a language model:
python -m spacy download en_core_web_sm
Also, the runtime depends on a local file called stop.txt which contains a list of stopwords. You can override this in the normalize_key_phrases() call.
License
PyTextRank has an Apache 2.0 license, so you can use it for commercial applications. Please let us know if you find this useful, and tell us about use cases, what else you’d like to see integrated, etc.
Here’s a Bibtex entry if you ever need to cite PyTextRank in a research paper:
@Misc{PyTextRank, author = {Nathan, Paco}, title = {PyTextRank, a Python implementation of TextRank for text document NLP parsing and summarization}, howpublished = {\url{https://github.com/ceteri/pytextrank/}}, year = {2016} }
Kudos
@htmartin @williamsmj @eugenep @mattkohl @vanita5 @HarshGrandeur @mnowotka @kjam @dvsrepo @dimmu @laxatives @SaiThejeshwar
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for pytextrank-1.2.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 67ca0feeaed8d83ac09fe8a20ac64f280364c1db26464f8405508cb7a2ad5a1d |
|
MD5 | d3bbf104f15a5b6b705857a22f3cb909 |
|
BLAKE2b-256 | b1428a769f6b0655ef9c2dc6a49919ab09f0d7795739b3e95c6b98cb744d3674 |