Semantic Parsing Natural Language into Relational Algebra

TL;DR

This paper explores neural sequence-to-sequence models for converting natural language into relational algebra for database querying, aiming to improve generalization over traditional rule-based methods.

Contribution

It evaluates various neural sequence-to-sequence models for semantic parsing into relational algebra, demonstrating their potential for more scalable NLIDB systems.

Findings

Neural models show promising generalization capabilities.

Sequence-to-sequence approaches outperform traditional rule-based methods.

Evaluation on multiple datasets confirms effectiveness.

Abstract

Natural interface to database (NLIDB) has been researched a lot during the past decades. In the core of NLIDB, is a semantic parser used to convert natural language into SQL. Solutions from traditional NLP methodology focuses on grammar rule pattern learning and pairing via intermediate logic forms. Although those methods give an acceptable performance on certain specific database and parsing tasks, they are hard to generalize and scale. On the other hand, recent progress in neural deep learning seems to provide a promising direction towards building a general NLIDB system. Unlike the traditional approach, those neural methodologies treat the parsing problem as a sequence-to-sequence learning problem. In this paper, we experimented on several sequence-to-sequence learning models and evaluate their performance on general database parsing task.