A Survey on Semantic Parsing

TL;DR

This survey reviews the evolution of semantic parsing from rule-based methods to neural approaches, emphasizing challenges and supervision levels in converting natural language to executable logical forms for knowledge bases.

Contribution

It provides a comprehensive overview of semantic parsing techniques, highlighting recent neural methods and discussing key challenges and supervision strategies.

Findings

Neural approaches have advanced semantic parsing significantly.

Supervision levels impact the effectiveness of parsing models.

Key challenges include ambiguity and data scarcity.

Abstract

A significant amount of information in today's world is stored in structured and semi-structured knowledge bases. Efficient and simple methods to query them are essential and must not be restricted to only those who have expertise in formal query languages. The field of semantic parsing deals with converting natural language utterances to logical forms that can be easily executed on a knowledge base. In this survey, we examine the various components of a semantic parsing system and discuss prominent work ranging from the initial rule based methods to the current neural approaches to program synthesis. We also discuss methods that operate using varying levels of supervision and highlight the key challenges involved in the learning of such systems.