StructVAE: Tree-structured Latent Variable Models for Semi-supervised Semantic Parsing

TL;DR

StructVAE is a semi-supervised model that leverages unlabeled data to improve semantic parsing by modeling tree-structured latent variables, outperforming supervised models on ATIS and Python code tasks.

Contribution

Introduces StructVAE, a novel tree-structured variational auto-encoder for semi-supervised semantic parsing utilizing unlabeled data.

Findings

Outperforms supervised models with additional unlabeled data

Effective on ATIS domain and Python code generation

Models tree-structured latent variables for meaning representations

Abstract

Semantic parsing is the task of transducing natural language (NL) utterances into formal meaning representations (MRs), commonly represented as tree structures. Annotating NL utterances with their corresponding MRs is expensive and time-consuming, and thus the limited availability of labeled data often becomes the bottleneck of data-driven, supervised models. We introduce StructVAE, a variational auto-encoding model for semisupervised semantic parsing, which learns both from limited amounts of parallel data, and readily-available unlabeled NL utterances. StructVAE models latent MRs not observed in the unlabeled data as tree-structured latent variables. Experiments on semantic parsing on the ATIS domain and Python code generation show that with extra unlabeled data, StructVAE outperforms strong supervised models.