Robust Semantic Parsing with Adversarial Learning for Domain Generalization

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 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, then on PropBank Semantic Role Labeling task on the CoNLL-2005 benchmark. We show that adversarial learning increases all models generalization capabilities both on in and out-of-domain data.
Complete list of metadatas

Cited literature [26 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02298402
Contributor : Gabriel Marzinotto <>
Submitted on : Friday, September 27, 2019 - 1:30:35 PM
Last modification on : Wednesday, October 2, 2019 - 1:29:21 AM

Files

naaclhlt2019.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Gabriel Marzinotto, Geraldine Damnati, Frédéric Béchet, Benoit Favre. Robust Semantic Parsing with Adversarial Learning for Domain Generalization. Proceedings of the 2019 Conference of the North, Jun 2019, Minneapolis - Minnesota, France. pp.166-173, ⟨10.18653/v1/N19-2021⟩. ⟨hal-02298402⟩

Share

Metrics

Record views

43

Files downloads

50