Dependency Chart Parsing Algorithm Based on Ternary-Span Combination
Summary :
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.
- Publication
- IEICE TRANSACTIONS on Information Vol.E96-D No.1 pp.93-101
- Publication Date
- 2013/01/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.E96.D.93
- Type of Manuscript
- PAPER
- Category
- Natural Language Processing
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Meixun JIN, Yong-Hun LEE, Jong-Hyeok LEE, "Dependency Chart Parsing Algorithm Based on Ternary-Span Combination" in IEICE TRANSACTIONS on Information,
vol. E96-D, no. 1, pp. 93-101, January 2013, doi: 10.1587/transinf.E96.D.93.
Abstract: 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.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E96.D.93/_p
Copy
@ARTICLE{e96-d_1_93,
author={Meixun JIN, Yong-Hun LEE, Jong-Hyeok LEE, },
journal={IEICE TRANSACTIONS on Information},
title={Dependency Chart Parsing Algorithm Based on Ternary-Span Combination},
year={2013},
volume={E96-D},
number={1},
pages={93-101},
abstract={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.},
keywords={},
doi={10.1587/transinf.E96.D.93},
ISSN={1745-1361},
month={January},}
Copy
TY - JOUR
TI - Dependency Chart Parsing Algorithm Based on Ternary-Span Combination
T2 - IEICE TRANSACTIONS on Information
SP - 93
EP - 101
AU - Meixun JIN
AU - Yong-Hun LEE
AU - Jong-Hyeok LEE
PY - 2013
DO - 10.1587/transinf.E96.D.93
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E96-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2013
AB - 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.
ER -
English
