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
Editors:
Mirella Lapata, Phil Blunsom, Alexander Koller
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
331–336
Language:
URL:
https://aclanthology.org/E17-2053
DOI:
Bibkey:
Cite (ACL):
Maximin Coavoux and Benoît Crabbé. 2017. Multilingual Lexicalized Constituency Parsing with Word-Level Auxiliary Tasks. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 331–336, Valencia, Spain. Association for Computational Linguistics.
Cite (Informal):
Multilingual Lexicalized Constituency Parsing with Word-Level Auxiliary Tasks (Coavoux & Crabbé, EACL 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/ml4al-ingestion/E17-2053.pdf
Code
 mcoavoux/mtg