Zhitao Hou


2024

pdf
NL2Formula: Generating Spreadsheet Formulas from Natural Language Queries
Wei Zhao | Zhitao Hou | Siyuan Wu | Yan Gao | Haoyu Dong | Yao Wan | Hongyu Zhang | Yulei Sui | Haidong Zhang
Findings of the Association for Computational Linguistics: EACL 2024

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 fCoder. Experimental results validate the effectiveness of fCoder, demonstrating its superior performance compared to the baseline models. Furthermore, we also compare fCoder with an initial GPT-3.5 model (i.e., text-davinci-003). Lastly, through in-depth error analysis, we identify potential challenges in the NL2Formula task and advocate for further investigation.

2023

pdf
HermEs: Interactive Spreadsheet Formula Prediction via Hierarchical Formulet Expansion
Wanrong He | Haoyu Dong | Yihuai Gao | Zhichao Fan | Xingzhuo Guo | Zhitao Hou | Xiao Lv | Ran Jia | Shi Han | Dongmei Zhang
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

We propose HermEs, the first approach for spreadsheet formula prediction via HiEraRchical forMulet ExpanSion, where hierarchical expansion means generating formulas following the underlying parse tree structure, and Formulet refers to commonly-used multi-level patterns mined from real formula parse trees. HermEs improves the formula prediction accuracy by (1) guaranteeing correct grammar by hierarchical generation rather than left-to-right generation and (2) significantly streamlining the token-level decoding with high-level Formulet. Notably, instead of generating formulas in a pre-defined fixed order, we propose a novel sampling strategy to systematically exploit a variety of hierarchical and multi-level expansion orders and provided solid mathematical proof, with the aim of meeting diverse human needs of the formula writing order in real applications. We further develop an interactive formula completion interface based on HermEs, which shows a new user experience in https://github.com/formulet/HERMES.