Semantics as a Foreign Language

Gabriel Stanovsky, Ido Dagan


Abstract
We propose a novel approach to semantic dependency parsing (SDP) by casting the task as an instance of multi-lingual machine translation, where each semantic representation is a different foreign dialect. To that end, we first generalize syntactic linearization techniques to account for the richer semantic dependency graph structure. Following, we design a neural sequence-to-sequence framework which can effectively recover our graph linearizations, performing almost on-par with previous SDP state-of-the-art while requiring less parallel training annotations. Beyond SDP, our linearization technique opens the door to integration of graph-based semantic representations as features in neural models for downstream applications.
Anthology ID:
D18-1263
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2412–2421
Language:
URL:
https://www.aclweb.org/anthology/D18-1263
DOI:
10.18653/v1/D18-1263
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D18-1263.pdf
Video:
 https://vimeo.com/306045906