Unlexicalized Transition-based Discontinuous Constituency Parsing

Maximin Coavoux, Benoît Crabbé, Shay B. Cohen


Abstract
Lexicalized parsing models are based on the assumptions that (i) constituents are organized around a lexical head and (ii) bilexical statistics are crucial to solve ambiguities. In this paper, we introduce an unlexicalized transition-based parser for discontinuous constituency structures, based on a structure-label transition system and a bi-LSTM scoring system. We compare it with lexicalized parsing models in order to address the question of lexicalization in the context of discontinuous constituency parsing. Our experiments show that unlexicalized models systematically achieve higher results than lexicalized models, and provide additional empirical evidence that lexicalization is not necessary to achieve strong parsing results. Our best unlexicalized model sets a new state of the art on English and German discontinuous constituency treebanks. We further provide a per-phenomenon analysis of its errors on discontinuous constituents.
Anthology ID:
Q19-1005
Volume:
Transactions of the Association for Computational Linguistics, Volume 7
Month:
Year:
2019
Address:
Cambridge, MA
Editors:
Lillian Lee, Mark Johnson, Brian Roark, Ani Nenkova
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
73–89
Language:
URL:
https://aclanthology.org/Q19-1005
DOI:
10.1162/tacl_a_00255
Bibkey:
Cite (ACL):
Maximin Coavoux, Benoît Crabbé, and Shay B. Cohen. 2019. Unlexicalized Transition-based Discontinuous Constituency Parsing. Transactions of the Association for Computational Linguistics, 7:73–89.
Cite (Informal):
Unlexicalized Transition-based Discontinuous Constituency Parsing (Coavoux et al., TACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/Q19-1005.pdf
Code
 mcoavoux/mtg_TACL
Data
Penn Treebank