A Natural Language Interface for Efficient Data Retrieval in SDSS

TL;DR

This paper presents a natural language interface for SDSS that uses a fine-tuned transformer model to translate user queries into SQL, making data retrieval accessible to non-experts.

Contribution

It introduces a novel approach of fine-tuning a compact transformer model on domain-specific NL-SQL pairs for astronomical data retrieval.

Findings

Model produces syntactically valid SQL queries

High semantic accuracy in translating user requests

Effective for diverse astronomy data queries

Abstract

Modern astronomical surveys such as the Sloan Digital Sky Survey (SDSS) provide extensive astronomical databases enabling researchers to access vast amount of diverse data. However, retrieving data from archives requires knowledge of query languages and familiarity with their schema, which presents a barrier for non-experts. This work investigates the use of Microsoft Phi-2, a compact yet powerful transformer-based language model, fine-tuned on natural language--SQL pairs constructed from SDSS query examples. We develop an interface that translates user queries in natural language into SQL commands compatible with SDSS SkyServer. Preliminary evaluation shows that the fine-tuned model produces syntactically valid and largely semantically correct queries across a variety of astronomy-related requests. Our results show that even small-scale models, when carefully fine-tuned, can provide effective domain-specific natural language interfaces for large scientific databases.