Initial Explorations of CCG Supertagging for Universal Dependency Parsing

Burak Kerim Akkus, Heval Azizoglu, Ruket Cakici


Abstract
In this paper we describe the system by METU team for universal dependency parsing of multilingual text. We use a neural network-based dependency parser that has a greedy transition approach to dependency parsing. CCG supertags contain rich structural information that proves useful in certain NLP tasks. We experiment with CCG supertags as additional features in our experiments. The neural network parser is trained together with dependencies and simplified CCG tags as well as other features provided.
Anthology ID:
K17-3023
Volume:
Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
Month:
August
Year:
2017
Address:
Vancouver, Canada
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
218–227
Language:
URL:
https://aclanthology.org/K17-3023
DOI:
10.18653/v1/K17-3023
Bibkey:
Cite (ACL):
Burak Kerim Akkus, Heval Azizoglu, and Ruket Cakici. 2017. Initial Explorations of CCG Supertagging for Universal Dependency Parsing. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pages 218–227, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
Initial Explorations of CCG Supertagging for Universal Dependency Parsing (Akkus et al., CoNLL 2017)
Copy Citation:
PDF:
https://aclanthology.org/K17-3023.pdf
Data
Penn TreebankUniversal Dependencies