Skip to main content

Unsupervised Discovery of Rhyme Schemes

Project description


A python package for detecting rhyme schemes in poetry. With standard configuration, it achieves about 65% accuracy in the rhymedata corpus.

Basic usage

pip install rhymediscovery
>>> from rhymediscovery import find_schemes
>>> find_schemes.find_schemes([['herz', 'welt', 'geld', 'schmerz'], ...])
[(('herz', 'welt', 'geld', 'schmerz'), (1, 2, 1, 2)), ...]

Command line

The command line tool find_schemes expects a file formatted like the .pgold files in the rhymedata corpus. A sample file can be found here in the repo.

To demonstrate the tool, we clone the rhymedata corpus:

git clone

Then we run:

find_schemes rhymedata/english_gold/1415.pgold 1415.out

The 1415.pgold file from the corpus has been manually annotated with the correct rhyme schemes. Thus we can evaluate our result file using:

evaluate_schemes 1415.out rhymedata/english_gold/1415.pgold


This package implements the following paper:

  • Sravana Reddy and Kevin Knight. “Unsupervised discovery of rhyme schemes.” Proceedings of ACL 2011. (pdf)

It is a fork of the reference implementation by @sravanareddy which is available in its original form here.

Project details

Release history Release notifications

This version
History Node


History Node


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Filename, size & hash SHA256 hash help File type Python version Upload date
rhymediscovery-0.2.1.tar.gz (12.4 kB) Copy SHA256 hash SHA256 Source None Jun 11, 2016

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging CloudAMQP CloudAMQP RabbitMQ AWS AWS Cloud computing Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page