Language to Logical Form with Neural Attention

TL;DR

This paper introduces an attention-based neural encoder-decoder model for semantic parsing that maps natural language to logical forms, achieving competitive results without handcrafted features across multiple datasets.

Contribution

It presents a general neural approach for semantic parsing that reduces reliance on domain-specific resources and manual feature engineering.

Findings

Competitive performance on four datasets

No need for handcrafted features

Easy adaptation across domains

Abstract

Semantic parsing aims at mapping natural language to machine interpretable meaning representations. Traditional approaches rely on high-quality lexicons, manually-built templates, and linguistic features which are either domain- or representation-specific. In this paper we present a general method based on an attention-enhanced encoder-decoder model. We encode input utterances into vector representations, and generate their logical forms by conditioning the output sequences or trees on the encoding vectors. Experimental results on four datasets show that our approach performs competitively without using hand-engineered features and is easy to adapt across domains and meaning representations.