Meta-Learning for Domain Generalization in Semantic Parsing
원문 초록
The importance of building semantic parsers which can be applied to new domains and generate programs unseen at training has long been acknowledged, and datasets testing out-of-domain performance are becoming increasingly available. However, little or no attention has been devoted to learning algorithms or objectives which promote domain generalization, with virtually all existing approaches relying on standard supervised learning. In this work, we use a meta-learning framework which targets zero-shot domain generalization for semantic parsing. We apply a model-agnostic training algorithm that simulates zero-shot parsing by constructing virtual train and test sets from disjoint domains. The learning objective capitalizes on the intuition that gradient steps that improve source-domain performance should also improve target-domain performance, thus encouraging a parser to generalize to unseen target domains. Experimental results on the (English) Spider and Chinese Spider datasets show that the meta-learning objective significantly boosts the performance of a baseline parser.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Balanced Direction from Multifarious Choices: Arithmetic Meta-Learning for Domain Generalization
CLIP-aware Domain-Adaptive Super-Resolution
InstructFLIP: Exploring Unified Vision-Language Model for Face Anti-spoofing
Geo-ORBIT: A Federated Digital Twin Framework for Scene-Adaptive Lane Geometry Detection
Prompt-Free Conditional Diffusion for Multi-object Image Augmentation
Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion
토론
이 논문과 연결된 포럼 글이 아직 없습니다.