tech,4-1-N03-2015,bq model </term> . We describe a simple <term> unsupervised technique </term> for learning <term> morphology </term>
other,8-1-N03-2015,bq unsupervised technique </term> for learning <term> morphology </term> by identifying <term> hubs </term> in
other,11-1-N03-2015,bq <term> morphology </term> by identifying <term> hubs </term> in an <term> automaton </term> . For
tech,14-1-N03-2015,bq identifying <term> hubs </term> in an <term> automaton </term> . For our purposes , a <term> hub </term>
other,5-2-N03-2015,bq automaton </term> . For our purposes , a <term> hub </term> is a <term> node </term> in a <term> graph
other,8-2-N03-2015,bq our purposes , a <term> hub </term> is a <term> node </term> in a <term> graph </term> with <term> in-degree
other,11-2-N03-2015,bq hub </term> is a <term> node </term> in a <term> graph </term> with <term> in-degree </term> greater
other,13-2-N03-2015,bq node </term> in a <term> graph </term> with <term> in-degree </term> greater than one and <term> out-degree
other,18-2-N03-2015,bq in-degree </term> greater than one and <term> out-degree </term> greater than one . We create a <term>
other,3-3-N03-2015,bq </term> greater than one . We create a <term> word-trie </term> , transform it into a <term> minimal
other,9-3-N03-2015,bq word-trie </term> , transform it into a <term> minimal DFA </term> , then identify <term> hubs </term> .
other,14-3-N03-2015,bq <term> minimal DFA </term> , then identify <term> hubs </term> . Those <term> hubs </term> mark the
other,1-4-N03-2015,bq then identify <term> hubs </term> . Those <term> hubs </term> mark the boundary between <term> root
other,6-4-N03-2015,bq hubs </term> mark the boundary between <term> root </term> and <term> suffix </term> , achieving
other,8-4-N03-2015,bq boundary between <term> root </term> and <term> suffix </term> , achieving similar <term> performance
other,12-4-N03-2015,bq <term> suffix </term> , achieving similar <term> performance </term> to more complex mixtures of techniques
hide detail