A Novel Probabilistic Model for Dependency Parsing

Free registration required

Executive Summary

A new Knowledge based Probabilistic Dependency Parsing (KPDP) is presented to overcome the local optimization problem of native probabilistic models. KPDP is composed of two stages: selecting a set of constituent parse trees with an extensive bottom-up chart parsing algorithm which employs Maximum Entropy Models to calculate single arc probabilities; finding the best parsing tree with the help of word knowledge. Different from previous studies, the authors incorporate word knowledge into parsing procedure. Based on case grammar theory, the word knowledge is represented as some patterns which group those arcs with the same head.

  • Format: PDF
  • Size: 591.4 KB