SpreadsheetCoder: Formula Prediction from Semi-structured Context

By Xinyun Chen, Petros Maniatis, Rishabh Singh, Charles Sutton, Hanjun Dai, Maxwell Lin, Denny Zhou. 2021

65 citations recorded by the source corpus.

Spreadsheet formula prediction has been an important program synthesis problem with many real-world applications. Previous works typically utilize input-output examples as the specification for spreadsheet formula synthesis, where each input-output pair simulates a separate row in the spreadsheet. However, this formulation does not fully capture the rich context in real-world spreadsheets. First, spreadsheet data entries are organized as tables, thus rows and columns are not necessarily independent from each other. In addition, many spreadsheet tables include headers, which provide high-level descriptions of the cell data. However, previous synthesis approaches do not consider headers as part of the specification. In this work, we present the first approach for synthesizing spreadsheet formulas from tabular context, which includes both headers and semi-structured tabular data. In particular, we propose SpreadsheetCoder, a BERT-based model architecture to represent the tabular context in both row-based and column-based formats. We train our model on a large dataset of spreadsheets, and demonstrate that SpreadsheetCoder achieves top-1 prediction accuracy of 42.51%, which is a considerable improvement over baselines that do not employ rich tabular context. Compared to the rule-based system, SpreadsheetCoder assists 82% more users in composing formulas on Google Sheets.

Subfields: Software, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Software

In Natural Language Processing

Citations in the corpus

InCoder: A Generative Model for Code Infilling and Synthesis (2022, background): “, input-output examples [12, 28, 19, 13], partial implementations [58], or natural language descriptions [74, 73, 72, 42, 18] of the desired program as input.”
High-throughput Generative Inference of Large Language Models with a Single GPU (2023, background): “In addition to interactive use cases such as chatbots, LLMs are also applied to many “back-of-house” tasks such as benchmarking (Liang et al., 2022), information extraction (Narayan et al., 2018), data wrangling (Narayan et al., 2022), and form processing (Chen et al., 2021).”
Learning to Synthesize Programs as Interpretable and Generalizable Policies (2021, background): “[57] Xinyun Chen, Petros Maniatis, Rishabh Singh, Charles Sutton, Hanjun Dai, Max Lin, and Denny Zhou.”
Natural Language to Code Generation in Interactive Data Science Notebooks (2022, methodology): “LLMs for Code In recent years there has been a burgeoning of LMs trained on code (Chen et al., 2021a; Austin et al., 2021; Nijkamp et al., 2022; Fried et al., 2022; Li et al., 2022; Tunstall et al., 2022; Xu et al., 2022).”