Language Independent Dependency to Constituent Tree Conversion

Young-Suk Lee, Zhiguo Wang


Abstract
We present a dependency to constituent tree conversion technique that aims to improve constituent parsing accuracies by leveraging dependency treebanks available in a wide variety in many languages. The technique works in two steps. First, a partial constituent tree is derived from a dependency tree with a very simple deterministic algorithm that is both language and dependency type independent. Second, a complete high accuracy constituent tree is derived with a constraint-based parser, which uses the partial constituent tree as external constraints. Evaluated on Section 22 of the WSJ Treebank, the technique achieves the state-of-the-art conversion F-score 95.6. When applied to English Universal Dependency treebank and German CoNLL2006 treebank, the converted treebanks added to the human-annotated constituent parser training corpus improve parsing F-scores significantly for both languages.
Anthology ID:
C16-1041
Volume:
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
Month:
December
Year:
2016
Address:
Osaka, Japan
Editors:
Yuji Matsumoto, Rashmi Prasad
Venue:
COLING
SIG:
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
421–428
Language:
URL:
https://aclanthology.org/C16-1041
DOI:
Bibkey:
Cite (ACL):
Young-Suk Lee and Zhiguo Wang. 2016. Language Independent Dependency to Constituent Tree Conversion. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 421–428, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
Language Independent Dependency to Constituent Tree Conversion (Lee & Wang, COLING 2016)
Copy Citation:
PDF:
https://aclanthology.org/C16-1041.pdf
Data
Penn Treebank