| tech,4-1-N03-2015,ak | model </term> . We describe a simple <term> | unsupervised technique | </term> for learning <term> morphology </term> | #3158 We describe a simpleunsupervised technique for learning morphology by identifying hubs in an automaton. | |
| other,11-1-N03-2015,ak | <term> morphology </term> by identifying <term> | hubs | </term> in an <term> automaton </term> . For | #3165 We describe a simple unsupervised technique for learning morphology by identifyinghubs in an automaton. | |
| other,13-2-N03-2015,ak | node </term> in a <term> graph </term> with <term> | in-degree | </term> greater than one and <term> out-degree | #3183 For our purposes, a hub is a node in a graph within-degree greater than one and out-degree greater than one. | |
| other,9-3-N03-2015,ak | word-trie </term> , transform it into a <term> | minimal DFA | </term> , then identify <term> hubs </term> . | #3202 We create a word-trie, transform it into aminimal DFA, then identify hubs. | |
| other,14-3-N03-2015,ak | <term> minimal DFA </term> , then identify <term> | hubs | </term> . Those <term> hubs </term> mark the | #3207 We create a word-trie, transform it into a minimal DFA, then identifyhubs. | |
| other,1-4-N03-2015,ak | then identify <term> hubs </term> . Those <term> | hubs | </term> mark the boundary between <term> root | #3210 Thosehubs mark the boundary between root and suffix, achieving similar performance to more complex mixtures of techniques. |
