Yong-Seok Choi, Kong Joo Lee

KIPS Transactions on Software and Data Engineering, Vol. 10, No. 6, pp. 235-242, Jun. 2021
https://doi.org/10.3745/KTSDE.2021.10.6.235,   PDF Download:   Full Text
Keywords: Stack-Pointer Networks, Korean Dependency Parser, Graph Attention Networks, Subtree, Pre-trained Word RepresentationModel, Everyone’s Corpus
Abstract

In this work, we develop a Korean dependency parser based on a stack-pointer network that consists of a pointer network and an internal stack. The parser has an encoder and decoder and builds a dependency tree for an input sentence in a depth-first manner. The encoder of the parser encodes an input sentence, and the decoder selects a child for the word at the top of the stack at each step. Since the parser has the internal stack where a search path is stored, the parser can utilize information of previously derived subtrees when selecting a child node. Previous studies used only a grandparent and the most recently visited sibling without considering a subtree structure. In this paper, we introduce graph attention networks that can represent a previously derived subtree. Then we modify our parser based on the stack-pointer network to utilize subtree information produced by the graph attention networks. After training the dependency parser using Sejong and Everyone’s corpus, we evaluate the parser’s performance. Experimental results show that the proposed parser achieves better performance than the previous approaches at sentence-level accuracies when adopting 2-depth graph attention networks.

Statistics
Cite this article