Multilingual Lexicalized Constituency Parsing with Word-Level Auxiliary Tasks

Maximin Coavoux, Benoît Crabbé


Abstract
We introduce a constituency parser based on a bi-LSTM encoder adapted from recent work (Cross and Huang, 2016b; Kiperwasser and Goldberg, 2016), which can incorporate a lower level character biLSTM (Ballesteros et al., 2015; Plank et al., 2016). We model two important interfaces of constituency parsing with auxiliary tasks supervised at the word level: (i) part-of-speech (POS) and morphological tagging, (ii) functional label prediction. On the SPMRL dataset, our parser obtains above state-of-the-art results on constituency parsing without requiring either predicted POS or morphological tags, and outputs labelled dependency trees.
Anthology ID:
E17-2053
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
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
331–336
Language:
URL:
https://www.aclweb.org/anthology/E17-2053
DOI:
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/E17-2053.pdf