Analysis of the difficulties in Chinese deep parsing

Authors:
Kun Yu;Yusuke Miyao;Takuya Matsuzaki;Xiangli Wang;Junichi Tsujii
Affiliations:
The University of Tokyo, Tokyo, Japan;National Institute of Informatics, Tokyo, Japan;The University of Tokyo, Tokyo, Japan;Japan Patent Information Organization, Tokyo, Japan;Microsoft Research Asia, Beijing, P. R. China
Venue:
IWPT '11 Proceedings of the 12th International Conference on Parsing Technologies
Year:
2011

Citing 23
Cited 3

A syntactic analysis method of long Japanese sentences based on the detection of conjunctive structures

Computational Linguistics
The syntactic process

The syntactic process
Building a large annotated corpus of English: the penn treebank

Computational Linguistics - Special issue on using large corpora: II
The Penn Chinese TreeBank: Phrase structure annotation of a large corpus

Natural Language Engineering
Is it harder to parse Chinese, or the Chinese Treebank?

ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Large-Scale Induction and Evaluation of Lexical Resources from the Penn-II and Penn-III Treebanks

Computational Linguistics
Parsing the WSJ using CCG and log-linear models

ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
Feature forest models for probabilistic hpsg parsing

Computational Linguistics
Semantic role labeling: an introduction to the special issue

Computational Linguistics
Adding semantic roles to the chinese treebank

Natural Language Engineering
Multilingual dependency analysis with a two-stage discriminative parser

CoNLL-X '06 Proceedings of the Tenth Conference on Computational Natural Language Learning
The CoNLL-2009 shared task: syntactic and semantic dependencies in multiple languages

CoNLL '09 Proceedings of the Thirteenth Conference on Computational Natural Language Learning: Shared Task
An iterative approach for joint dependency parsing and semantic role labeling

CoNLL '09 Proceedings of the Thirteenth Conference on Computational Natural Language Learning: Shared Task
A latent variable model of synchronous syntactic-semantic parsing for multiple languages

CoNLL '09 Proceedings of the Thirteenth Conference on Computational Natural Language Learning: Shared Task
Multilingual semantic role labeling

CoNLL '09 Proceedings of the Thirteenth Conference on Computational Natural Language Learning: Shared Task
Multilingual dependency learning: a huge feature engineering method to semantic dependency parsing

CoNLL '09 Proceedings of the Thirteenth Conference on Computational Natural Language Learning: Shared Task
A second-order joint eisner model for syntactic and semantic dependency parsing

CoNLL '09 Proceedings of the Thirteenth Conference on Computational Natural Language Learning: Shared Task
Multilingual semantic role labelling with Markov logic

CoNLL '09 Proceedings of the Thirteenth Conference on Computational Natural Language Learning: Shared Task
A simple generative pipeline approach to dependency parsing and semantic role labeling

CoNLL '09 Proceedings of the Thirteenth Conference on Computational Natural Language Learning: Shared Task
Efficient HPSG parsing with supertagging and CFG-filtering

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Joint syntactic and semantic parsing of Chinese

ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Chinese CCGbank: extracting CCG derivations from the Penn Chinese Treebank

COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics
Semi-automatically developing Chinese HPSG grammar from the Penn Chinese Treebank for deep parsing

COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics: Posters

The challenges of parsing Chinese with combinatory categorial grammar

NAACL HLT '12 Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Parser showdown at the wall street corral: an empirical investigation of error types in parser output

EMNLP-CoNLL '12 Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning
Head finalization reordering for Chinese-to-Japanese machine translation

SSST-6 '12 Proceedings of the Sixth Workshop on Syntax, Semantics and Structure in Statistical Translation

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper discusses the difficulties in Chinese deep parsing, by comparing the accuracy of a Chinese HPSG parser to the accuracy of an English HPSG parser and the commonly used Chinese syntactic parsers. Analysis reveals that deep parsing for Chinese is more challenging than for English, due to the shortage of syntactic constraints of Chinese verbs, the widespread pro-drop, and the large distribution of ambiguous constructions. Moreover, the inherent ambiguities caused by verbal co-ordination and relative clauses make semantic analysis of Chinese more difficult than the syntactic analysis of Chinese.