Coupling Retrieval and Meta-Learning for Context-Dependent Semantic Parsing
This addresses the problem of generating accurate semantic parses in context-dependent settings like code generation or conversational QA, but it is incremental as it builds on existing retrieval and meta-learning techniques.
The paper tackles context-dependent semantic parsing by combining a retrieval model and a meta-learner to use retrieved datapoints as supporting evidence, resulting in improved accuracy over baselines on CONCODE and CSQA datasets.
In this paper, we present an approach to incorporate retrieved datapoints as supporting evidence for context-dependent semantic parsing, such as generating source code conditioned on the class environment. Our approach naturally combines a retrieval model and a meta-learner, where the former learns to find similar datapoints from the training data, and the latter considers retrieved datapoints as a pseudo task for fast adaptation. Specifically, our retriever is a context-aware encoder-decoder model with a latent variable which takes context environment into consideration, and our meta-learner learns to utilize retrieved datapoints in a model-agnostic meta-learning paradigm for fast adaptation. We conduct experiments on CONCODE and CSQA datasets, where the context refers to class environment in JAVA codes and conversational history, respectively. We use sequence-to-action model as the base semantic parser, which performs the state-of-the-art accuracy on both datasets. Results show that both the context-aware retriever and the meta-learning strategy improve accuracy, and our approach performs better than retrieve-and-edit baselines.