Infusing Prompts with Syntax and Semantics
This work addresses the issue of improving language model accuracy for specific tasks like SQL translation, particularly benefiting low-resource language applications, though it appears incremental as it builds on existing linguistic analysis methods.
The paper tackles the problem of language models generating outputs with flawed linguistic structure by infusing syntactic and semantic information, showing that this approach significantly boosts performance in translating natural language queries to SQL for low-resource languages and surpasses previous best systems.
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.