[PDF][PDF] Unsupervised learning of morphology for English and Inuktitut
H Johnson, J Martin - Companion volume of the proceedings of …, 2003 - aclanthology.org
H Johnson, J Martin
Companion volume of the proceedings of HLT-NAACL 2003-short papers, 2003•aclanthology.orgWe 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 create 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 complex mixtures of techniques.
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 create 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 complex mixtures of techniques.
Abstract
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 create 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 complex mixtures of techniques.
aclanthology.org