Learning an Executable Neural Semantic Parser

TL;DR

This paper introduces a neural semantic parser that converts natural language into executable logical forms using a transition-based, tree-generation approach with neural networks, attention mechanisms, and various training methods.

Contribution

It presents a novel neural semantic parsing framework that handles logical form generation with structured neural models and explores multiple training paradigms for improved performance.

Findings

Effective across diverse datasets

Outperforms previous semantic parsers

Flexible training methods enhance applicability

Abstract

This paper describes a neural semantic parser that maps natural language utterances onto logical forms which can be executed against a task-specific environment, such as a knowledge base or a database, to produce a response. The parser generates tree-structured logical forms with a transition-based approach which combines a generic tree-generation algorithm with domain-general operations defined by the logical language. The generation process is modeled by structured recurrent neural networks, which provide a rich encoding of the sentential context and generation history for making predictions. To tackle mismatches between natural language and logical form tokens, various attention mechanisms are explored. Finally, we consider different training settings for the neural semantic parser, including a fully supervised training where annotated logical forms are given, weakly-supervised training where denotations are provided, and distant supervision where only unlabeled sentences and a knowledge base are available. Experiments across a wide range of datasets demonstrate the effectiveness of our parser.