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:
- 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)
- PDF:
- https://preview.aclanthology.org/landing_page/C16-1041.pdf
- Data
- Penn Treebank