Neural Generation of Regular Expressions from Natural Language with Minimal Domain Knowledge

TL;DR

This paper presents a neural approach to translating natural language queries into regular expressions without domain-specific knowledge, utilizing a large corpus for training, and achieving significant performance improvements.

Contribution

The paper introduces a neural model that learns to generate regular expressions from natural language without domain-specific crafting, supported by a new large corpus of paired data.

Findings

Achieved a 19.6% performance improvement over previous models

Developed a methodology for collecting large regular expression and natural language pairs

Demonstrated the effectiveness of neural models in semantic translation tasks

Abstract

This paper explores the task of translating natural language queries into regular expressions which embody their meaning. In contrast to prior work, the proposed neural model does not utilize domain-specific crafting, learning to translate directly from a parallel corpus. To fully explore the potential of neural models, we propose a methodology for collecting a large corpus of regular expression, natural language pairs. Our resulting model achieves a performance gain of 19.6% over previous state-of-the-art models.