Meta-Learning for Domain Generalization in Semantic Parsing

10/22/2020
by   Bailin Wang, et al.
2

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 studying 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 specifically 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 well 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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/08/2021

Open Domain Generalization with Domain-Augmented Meta-Learning

Leveraging datasets available to learn a model with high generalization ...
research
04/03/2020

Sequential Learning for Domain Generalization

In this paper we propose a sequential learning framework for Domain Gene...
research
09/12/2019

Neural Semantic Parsing in Low-Resource Settings with Back-Translation and Meta-Learning

Neural semantic parsing has achieved impressive results in recent years,...
research
08/18/2020

Domain Generalizer: A Few-shot Meta Learning Framework for Domain Generalization in Medical Imaging

Deep learning models perform best when tested on target (test) data doma...
research
07/09/2019

Cross-Domain Generalization of Neural Constituency Parsers

Neural parsers obtain state-of-the-art results on benchmark treebanks fo...
research
07/04/2020

Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen Domains

Model generalization capacity at domain shift (e.g., various imaging pro...
research
02/07/2020

Meta-learning framework with applications to zero-shot time-series forecasting

Can meta-learning discover generic ways of processing time-series (TS) f...

Please sign up or login with your details

Forgot password? Click here to reset