Probabilistic graph-based dependency parsing with convolutional neural network

Abstract

This paper presents neural probabilistic parsing models which explore up to thirdorder graph-based parsing with maximum likelihood training criteria. Two neural network extensions are exploited for performance improvement. Firstly, a convolutional layer that absorbs the influences of all words in a sentence is used so that sentence-level information can be effectively captured. Secondly, a linear layer is added to integrate different order neural models and trained with perceptron method. The proposed parsers are evaluated on English and Chinese Penn Treebanks and obtain competitive accuracies.