A Feature-Rich Constituent Context Model for Grammar Induction
Dave Golland, John DeNero, Jakob Uszkoreit · 2012
We present LLCCM, a log-linear variant of the constituent context model (CCM) of grammar induction. LLCCM retains the simplicity of the original CCM but extends robustly to long sentences. On sentences of up to length 40, LLCCM outperforms CCM by 13.9 % bracketing F1 and outperforms a right-branching baseline in regimes where CCM does not. 1