TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation

TL;DR

TRANX is a neural semantic parser that converts natural language into formal meaning representations using a transition system based on abstract syntax, achieving high accuracy and adaptability across multiple tasks.

Contribution

Introduces TRANX, a transition-based neural parser leveraging abstract syntax descriptions for improved accuracy and generalizability in semantic parsing and code generation.

Findings

Achieves strong results on four semantic parsing and code generation tasks.

Demonstrates high accuracy by constraining output with syntax information.

Shows ease of adapting to new meaning representations by defining new syntax descriptions.

Abstract

We present TRANX, a transition-based neural semantic parser that maps natural language (NL) utterances into formal meaning representations (MRs). TRANX uses a transition system based on the abstract syntax description language for the target MR, which gives it two major advantages: (1) it is highly accurate, using information from the syntax of the target MR to constrain the output space and model the information flow, and (2) it is highly generalizable, and can easily be applied to new types of MR by just writing a new abstract syntax description corresponding to the allowable structures in the MR. Experiments on four different semantic parsing and code generation tasks show that our system is generalizable, extensible, and effective, registering strong results compared to existing neural semantic parsers.