Feature Support

Included is a variety of segmentation comparison metrics, including:

• Boundary Edit Distance (BED)

• Boundary Similarity (B)

• BED-based confusion matrices (and precision/recall/F1)

• Segmentation Similarity (S)

• WindowDiff

• Pk

Additionally, B-based inter-coder agreement coefficients for segmentation that are suitable for 2 or more coders are provided, including:

• Fleiss’ Pi (i.e., Siegel and Castellan’s K)

• Fleiss’ Kappa

Installation

To install SegEval, simply run:

$ pip install segeval

Documentation

Documentation is available at http://segeval.readthedocs.org/.

Citing SegEval

If you’re using this software for research, please cite the ACL paper [PDF] and, if you need to go into details, the thesis [PDF] describing this work:

• Chris Fournier. 2013. Evaluating Text Segmentation using Boundary Edit Distance. Proceedings of 51st Annual Meeting of the Association for Computational Linguistics. (ACL 2013), to appear. Association for Computational Linguistics, Stroudsburg, PA, USA.

• Chris Fournier. 2013. Evaluating Text Segmentation. (Master’s thesis). University of Ottawa.

BibTeX:

@inproceedings{Fournier2013a,
        author          = {Fournier, Chris},
        year            = {2013},
        title           = {{Evaluating Text Segmentation using Boundary Edit Distance}},
        booktitle       = {Proceedings of 51st Annual Meeting of the Association for Computational Linguistics},
        publisher       = {Association for Computational Linguistics},
        location        = {Sophia, Bulgaria},
        pages           = {to appear},
        address         = {Stroudsburg, PA, USA}
}

@mastersthesis{Fournier2013b,
        author          = {Fournier, Chris},
        title           = {Evaluating Text Segmentation},
        school          = {University of Ottawa},
        year            = {2013}
}