The Zebra System

This site contains information and resources related to Andrew Lampert's email text segmentation and classification research.

Zebra Image by arnolouise, licensed under Creative Commons

Zebra Email Segmentation Tool

The Zebra system is implemented in Java, using the following libraries and components:

• OpenNLP: We use an adaptation of OpenNLP's data structure for working with word ngram data
• SentParBreaker: Where required, we use Scott Piao's sentence segmenter, with a series of email-specific pre-processing rules, for performing sentence segmentation.
• Weka: We use Weka's SVM (SMO) implemention as our machine learner for Zebra.

The Zebra Email Segmentation Tool will be available for download. Right now, I'm working through some licensing issues before I can make it available. If you're keen to get a status update, please contact me.

Our annotated data is licensed under a Creative Commons Attribution-Noncommercial 2.0 Generic License.

If you make use of any of these resources, please cite the following paper:

Andrew Lampert, Robert Dale and Cécile Paris (2009) - Segmenting Email Message Text into Zones, In Proceedings of Empirical Methods in Natural Language Processing (EMNLP 2009), pp. 919-928, Singapore, August 6-7.