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

EMNLP 2018 Pengcheng YinGraham Neubig

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... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
Semantic Parsing ATIS Tranx Accuracy 86.2 # 1
Code Generation Django Tranx Accuracy 73.7 # 1
Semantic Parsing Geo Tranx Accuracy 87.7 # 1
Code Generation WikiSQL Tranx Execution Accuracy 78.6 # 1
Code Generation WikiSQL Tranx Exact Match Accuracy 68.6 # 1