Infusing Prompts with Syntax and Semantics

TL;DR

This paper explores how incorporating syntactic and semantic information into language models improves their performance, especially in translating natural language queries to SQL for less-resourced languages, surpassing previous systems.

Contribution

It introduces methods for infusing linguistic information into language models and demonstrates significant performance gains in NL-to-SQL translation tasks.

Findings

Linguistic infusion significantly improves translation accuracy.

Models surpass previous best systems in low-resource language translation.

Syntactic and semantic information enhances language understanding.

Abstract

Despite impressive success, language models often generate outputs with flawed linguistic structure. We analyze the effect of directly infusing various kinds of syntactic and semantic information into large language models. To demonstrate the value of our proposals, we focus on the translation of natural language queries to SQL, in particular dealing with languages with less resources than English, to better investigate how much help we can get from low cost syntactic and semantic information. We show that linguistic analysis can significantly boost language models, to the point that we have surpassed previous best systems.