Skip to main content

A package and utilities providing a variety of discourse segmentation evaluation metrics

Project description

This package is a collection of metrics and a command-line interface for evaluating segmentation. A variety of metrics are provided, including: Segmentation Similarity (S) (Fournier and Inkpen 2012); WindowDiff; Pk; and others.

Additionally, inter-coder agreement coefficients that are based upon S for both 2 and more coders are provided, including: Kappa; an Pi.

View the manual at: http://packages.python.org/segeval/

If you have any suggestions, problems, or difficulties, please log an issue, or contact me at:

For a roadmap of planned features and future work see my page on SegEval visit: http://nlp.chrisfournier.ca/software/segeval/

Project details


Download files

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

Source Distribution

segeval-1.0.1 beta.tar.gz (43.1 kB view details)

Uploaded Source

File details

Details for the file segeval-1.0.1 beta.tar.gz.

File metadata

File hashes

Hashes for segeval-1.0.1 beta.tar.gz
Algorithm Hash digest
SHA256 3878be8897658b203491a742fc2c18e0faf42b3a38180b149ba235cf60804cdc
MD5 38b8a0ff55751151fa71d26404e697d7
BLAKE2b-256 fc67a72131d37c0498125b64a9300455700c012bf911d190c8e5b5656821c16d

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page