Neural Generation of Regular Expressions from Natural Language with Minimal Domain Knowledge
This addresses the challenge of automating regex generation for users who need to process text patterns, representing a strong specific gain rather than a broad breakthrough.
The paper tackles the problem of translating natural language queries into regular expressions without domain-specific crafting, achieving a 19.6% performance gain over previous state-of-the-art models.
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.