Exploring Neural Methods for Parsing Discourse Representation Structures

Rik van Noord, Lasha Abzianidze, Antonio Toral, Johan Bos


Abstract
Neural methods have had several recent successes in semantic parsing, though they have yet to face the challenge of producing meaning representations based on formal semantics. We present a sequence-to-sequence neural semantic parser that is able to produce Discourse Representation Structures (DRSs) for English sentences with high accuracy, outperforming traditional DRS parsers. To facilitate the learning of the output, we represent DRSs as a sequence of flat clauses and introduce a method to verify that produced DRSs are well-formed and interpretable. We compare models using characters and words as input and see (somewhat surprisingly) that the former performs better than the latter. We show that eliminating variable names from the output using De Bruijn indices increases parser performance. Adding silver training data boosts performance even further.
Anthology ID:
Q18-1043
Volume:
Transactions of the Association for Computational Linguistics, Volume 6
Month:
Year:
2018
Address:
Cambridge, MA
Editors:
Lillian Lee, Mark Johnson, Kristina Toutanova, Brian Roark
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
619–633
Language:
URL:
https://aclanthology.org/Q18-1043
DOI:
10.1162/tacl_a_00241
Bibkey:
Cite (ACL):
Rik van Noord, Lasha Abzianidze, Antonio Toral, and Johan Bos. 2018. Exploring Neural Methods for Parsing Discourse Representation Structures. Transactions of the Association for Computational Linguistics, 6:619–633.
Cite (Informal):
Exploring Neural Methods for Parsing Discourse Representation Structures (van Noord et al., TACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/Q18-1043.pdf
Code
 RikVN/Neural_DRS