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

EMNLP 2018  ·  Pengcheng Yin, Graham 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. 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.

PDF Abstract EMNLP 2018 PDF EMNLP 2018 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Semantic Parsing ATIS Tranx Accuracy 86.2 # 2
Code Generation CoNaLa TranX BLEU 24.30 # 14
Code Generation CoNaLa-Ext TranX BLEU 18.85 # 6
Code Generation Django Tranx Accuracy 73.7 # 8
Semantic Parsing Geo Tranx Accuracy 87.7 # 3
Code Generation WikiSQL Tranx Execution Accuracy 78.6 # 3
Exact Match Accuracy 68.6 # 3

Methods


No methods listed for this paper. Add relevant methods here