Allomorfessor: Towards Unsupervised Morpheme Analysis

Many modern natural language processing applications would benefit from automatic morphological analysis of words, especially when dealing with morphologically rich languages. Consequently, there has been an increasing amount of research on the task of unsupervised segmentation of word forms into smaller useful units, i.e. morphs or morphemes. The linguistic phenomenon of allomorphy, where one morpheme has several different surface forms, places limits on the quality of morpheme analysis achievable by segmentation alone. We extend the morphological segmentation method, Morfessor Baseline, to model allomorphy. Our unsupervised method discovers common base forms for allomorphs from an unannotated corpus. We evaluate the method by participating in the Morpho Challenge 2008 competition, where automatic morphological analyses of corpora in English, German, Turkish and Finnish are compared against a linguistic gold standard. Our method achieves high precision, but low recall, and therefore ...

• Type: Conference
• Year: 2008
• Where: CLEF
• Authors: Oskar Kohonen, Sami Virpioja, Mikaela Klami
• Keywords: CLEF 2008, Information Management, Morphological Analysis, Morphological Segmentation Method, Natural Language Processing