Statistical Deep Parsing for Spanish Using Neural Networks

Luis Chiruzzo, Dina Wonsever


Abstract
This paper presents the development of a deep parser for Spanish that uses a HPSG grammar and returns trees that contain both syntactic and semantic information. The parsing process uses a top-down approach implemented using LSTM neural networks, and achieves good performance results in terms of syntactic constituency and dependency metrics, and also SRL. We describe the grammar, corpus and implementation of the parser. Our process outperforms a CKY baseline and other Spanish parsers in terms of global metrics and also for some specific Spanish phenomena, such as clitics reduplication and relative referents.
Anthology ID:
2020.iwpt-1.14
Volume:
Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies
Month:
July
Year:
2020
Address:
Online
Editors:
Gosse Bouma, Yuji Matsumoto, Stephan Oepen, Kenji Sagae, Djamé Seddah, Weiwei Sun, Anders Søgaard, Reut Tsarfaty, Dan Zeman
Venue:
IWPT
SIG:
SIGPARSE
Publisher:
Association for Computational Linguistics
Note:
Pages:
132–144
Language:
URL:
https://aclanthology.org/2020.iwpt-1.14
DOI:
10.18653/v1/2020.iwpt-1.14
Bibkey:
Cite (ACL):
Luis Chiruzzo and Dina Wonsever. 2020. Statistical Deep Parsing for Spanish Using Neural Networks. In Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies, pages 132–144, Online. Association for Computational Linguistics.
Cite (Informal):
Statistical Deep Parsing for Spanish Using Neural Networks (Chiruzzo & Wonsever, IWPT 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.iwpt-1.14.pdf
Video:
 http://slideslive.com/38929681