For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Dependency Chart Parsing Algorithm Based on Ternary-Span Combination
Meixun JIN Yong-Hun LEE Jong-Hyeok LEE
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2013/01/01
Online ISSN: 1745-1361
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Natural Language Processing
dependency chart parsing, span-based parsing, factor-based parsing, dependency parsing algorithm, averaged perceptron, syntactic analysis,
Full Text: PDF>>
This paper presents a new span-based dependency chart parsing algorithm that models the relations between the left and right dependents of a head. Such relations cannot be modeled in existing span-based algorithms, despite their popularity in dependency corpora. We address this problem through ternary-span combination during the subtree derivation. By modeling the relations between the left and right dependents of a head, our proposed algorithm provides a better capability of coordination disambiguation when the conjunction is annotated as the head of the left and right conjuncts. This eventually leads to state-of-the-art performance of dependency parsing on the Chinese data of the CoNLL shared task.