Robust Semantic Parsing with Adversarial Learning for Domain Generalization
This addresses the challenge of integrating semantic parsing technologies into real applications by enhancing robustness to inter-document variability, though it appears incremental as it builds on existing adversarial learning methods.
The paper tackled the problem of generalization in semantic parsing by using adversarial learning to increase robustness to lexical and stylistic variations, showing that it improves model generalization on both in-domain and out-of-domain data.
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.