Abstract

This article surveys work on Unsupervised Learning of Morphology. We define Unsupervised Learning of Morphology as the problem of inducing a description (of some kind, even if only morpheme-segmentation) of how orthographic words are built up given only raw text data of a language. We briefly go through the history and motivation of the this problem. Next, over 200 items of work are listed with a brief characterization, and the most important ideas in the field are critically discussed. We summarize the achievements so far and give pointers for future developments.

This content is only available as a PDF.

Author notes

*

Centre for Language Studies, Radboud Universiteit, Postbus 9103, 6500 HD Nijmegen, The Netherlands/Department of Linguistics, Max Planck Institute for Evolutionary Anthropology, Deutscher Platz 6, 04103 Leipzig, Germany. E-mail: h.hammarstrom@let.ru.nl.

*

Språkbanken, Department of Swedish Language, University of Gothenburg, Box 200, SE-405 30 Göteborg, Sweden. E-mail: lars.borin@svenska.gu.se.