Work

NL2Formula: Generating Spreadsheet Formulas from Natural Language Queries

Year: 2024

Type: conference-paper

Abstract: Writing formulas on spreadsheets, such as Microsoft Excel and Google Sheets, is a widespread practice among users performing data analysis.However, crafting formulas on spreadsheets remains a tedious and error-prone task for many end-users, particularly when dealing with complex operations.To alleviate the burden associated with writing spreadsheet formulas, this paper introduces a novel benchmark task called NL2FORMULA, with the aim to generate executable formulas that are grounded on a spreadsheet table, given a Natural Language (NL) query as input.To accomplish this, we construct a comprehensive dataset consisting of 70,799 paired NL queries and corresponding spreadsheet formulas, covering 21,670 tables and 37 types of formula functions.We realize the NL2FORMULA task by providing a sequence-to-sequence baseline implementation called f CODER.Experimental results validate the effectiveness of f CODER, demonstrating its superior performance compared to the baseline models.Furthermore, we also compare f CODER with an initial GPT-3.5 model (i.e., text-davinci-003).Lastly, through indepth error analysis, we identify potential challenges in the NL2FORMULA task and advocate for further investigation. 1

Source: Findings of the Association for Computational Linguistics: EACL

DOI: 10.18653/v1/2024.findings-eacl.158