Coupling Retrieval and Meta-Learning for Context-Dependent Semantic Parsing

Abstract

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.

Accepted by ACL 2019

References in corpus (9)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
• Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
• Hyperspherical Variational Auto-Encoders
• A Retrieve-and-Edit Framework for Predicting Structured Outputs
• Neural Programmer: Inducing Latent Programs with Gradient Descent
• Sequence-to-Action: End-to-End Semantic Graph Generation for Semantic Parsing
• Search Engine Guided Non-Parametric Neural Machine Translation
• Dictionary-Guided Editing Networks for Paraphrase Generation

Cited by in corpus (5)

• CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation
• CodeBLEU: a Method for Automatic Evaluation of Code Synthesis
• GraphCodeBERT: Pre-training Code Representations with Data Flow
• $k$Folden: $k$-Fold Ensemble for Out-Of-Distribution Detection
• Context Dependent Semantic Parsing: A Survey