Paper: Unsupervised Learning Of Morphology For English And Inuktitut

ACL ID N03-2015
Title Unsupervised Learning Of Morphology For English And Inuktitut
Venue Human Language Technologies
Session Short Paper
Year 2003
Authors

We describe a simple unsupervised technique for learning morphology by identifying hubs in an automaton. For our purposes, a hub is a node in a graph with in-degree greater than one and out-degree greater than one. We cre- ate a word-trie, transform it into a minimal DFA, then identify hubs. Those hubs mark the boundary between root and suffix, achieving similar performance to more com- plex mixtures of techniques.