A Morphology-Based Representation Model for LSTM-Based Dependency Parsing of Agglutinative Languages

Şaziye Betül Özateş, Arzucan Özgür, Tunga Güngör, Balkız Öztürk


Abstract
We propose two word representation models for agglutinative languages that better capture the similarities between words which have similar tasks in sentences. Our models highlight the morphological features in words and embed morphological information into their dense representations. We have tested our models on an LSTM-based dependency parser with character-based word embeddings proposed by Ballesteros et al. (2015). We participated in the CoNLL 2018 Shared Task on multilingual parsing from raw text to universal dependencies as the BOUN team. We show that our morphology-based embedding models improve the parsing performance for most of the agglutinative languages.
Anthology ID:
K18-2024
Volume:
Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
Month:
October
Year:
2018
Address:
Brussels, Belgium
Editors:
Daniel Zeman, Jan Hajič
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
238–247
Language:
URL:
https://aclanthology.org/K18-2024
DOI:
10.18653/v1/K18-2024
Bibkey:
Cite (ACL):
Şaziye Betül Özateş, Arzucan Özgür, Tunga Güngör, and Balkız Öztürk. 2018. A Morphology-Based Representation Model for LSTM-Based Dependency Parsing of Agglutinative Languages. In Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pages 238–247, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
A Morphology-Based Representation Model for LSTM-Based Dependency Parsing of Agglutinative Languages (Özateş et al., CoNLL 2018)
Copy Citation:
PDF:
https://aclanthology.org/K18-2024.pdf
Code
 CoNLL-UD-2018/BOUN
Data
Universal Dependencies