Robust Semantic Parsing with Adversarial Learning for Domain Generalization

Gabriel Marzinotto, Géraldine Damnati, Frédéric Béchet, Benoît Favre


Abstract
This paper addresses the issue of generalization for Semantic Parsing in an adversarial framework. Building models that are more robust to inter-document variability is crucial for the integration of Semantic Parsing technologies in real applications. The underlying question throughout this study is whether adversarial learning can be used to train models on a higher level of abstraction in order to increase their robustness to lexical and stylistic variations. We propose to perform Semantic Parsing with a domain classification adversarial task, covering various use-cases with or without explicit knowledge of the domain. The strategy is first evaluated on a French corpus of encyclopedic documents, annotated with FrameNet, in an information retrieval perspective. This corpus constitutes a new public benchmark, gathering documents from various thematic domains and various sources. We show that adversarial learning yields improved results when using explicit domain classification as the adversarial task. We also propose an unsupervised domain discovery approach that yields equivalent improvements. The latter is also evaluated on a PropBank Semantic Role Labeling task on the CoNLL-2005 benchmark and is shown to increase the model’s generalization capabilities on out-of-domain data.
Anthology ID:
N19-2021
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
166–173
Language:
URL:
https://www.aclweb.org/anthology/N19-2021
DOI:
10.18653/v1/N19-2021
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/N19-2021.pdf