Improving a Strong Neural Parser with Conjunction-Specific Features

Jessica Ficler, Yoav Goldberg


Abstract
While dependency parsers reach very high overall accuracy, some dependency relations are much harder than others. In particular, dependency parsers perform poorly in coordination construction (i.e., correctly attaching the conj relation). We extend a state-of-the-art dependency parser with conjunction-specific features, focusing on the similarity between the conjuncts head words. Training the extended parser yields an improvement in conj attachment as well as in overall dependency parsing accuracy on the Stanford dependency conversion of the Penn TreeBank.
Anthology ID:
E17-2055
Volume:
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
Month:
April
Year:
2017
Address:
Valencia, Spain
Editors:
Mirella Lapata, Phil Blunsom, Alexander Koller
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
343–348
Language:
URL:
https://aclanthology.org/E17-2055
DOI:
Bibkey:
Cite (ACL):
Jessica Ficler and Yoav Goldberg. 2017. Improving a Strong Neural Parser with Conjunction-Specific Features. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 343–348, Valencia, Spain. Association for Computational Linguistics.
Cite (Informal):
Improving a Strong Neural Parser with Conjunction-Specific Features (Ficler & Goldberg, EACL 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/ml4al-ingestion/E17-2055.pdf
Data
Penn Treebank