Paper: Painless Semi-Supervised Morphological Segmentation using Conditional Random Fields

ACL ID E14-4017
Title Painless Semi-Supervised Morphological Segmentation using Conditional Random Fields
Venue Annual Meeting of The European Chapter of The Association of Computational Linguistics
Session Main Conference
Year 2014
Authors

We discuss data-driven morphological segmentation, in which word forms are segmented into morphs, that is the surface forms of morphemes. We extend a re- cent segmentation approach based on con- ditional random fields from purely super- vised to semi-supervised learning by ex- ploiting available unsupervised segmenta- tion techniques. We integrate the unsu- pervised techniques into the conditional random field model via feature set aug- mentation. Experiments on three di- verse languages show that this straight- forward semi-supervised extension greatly improves the segmentation accuracy of the purely supervised CRFs in a computation- ally efficient manner.