Lexicalized Neural Unsupervised Dependency Parsing

Wenjuan Han

doi:10.1016/j.neucom.2019.04.012

2019-07-01

PRE

Wenjuan Han *

Yong Jiang

Kewei Tu

DOI：10.1016/j.neucom.2019.04.012

原文链接

原文求助

摘要

En 中文

Unsupervised dependency parsing is the task of learning a dependency grammar from a set of unannotated sentences. This paper describes a neural network (NN) based probabilistic model, Neural Dependency Model with Valence (NDMV), that combines the dependency parsing with the rich nonlinear featurization of NN approaches. NDMV follows the traditional DMV model and computes the probability of a grammar rule via a feed-forward NN. A strength of this proposed approach is the ability to learn the underlying features of input tokens. In our experiments, this capability leads to gains in both NDMV and its extension version, Lexicalized Neural Dependency Model with Valence (L-NDMV): NDMV achieves better performance on WSJ and datasets of eight additional languages in comparison with previous approaches in the basic setting; L-NDMV achieves a result that is competitive with the current state-of-the-art.(1) (C) 2019 Elsevier B.V. All rights reserved.

Keyword:

Unsupervised Dependency Parsing

Neural Network

Lexicalization