# Auto-completion for Data Cells in Relational Tables

arXiv: https://arxiv.org/abs/1909.03443 · HTML: https://mlsanity.com/paper/1909.03443/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Sep 2019.

## Built on by (most cited first, 9 of 9)

- [TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance](https://mlsanity.com/paper/2105.07624/) (2021)
- [TempTabQA: Temporal Question Answering for Semi-Structured Tables](https://mlsanity.com/paper/2311.08002/) (2023)
- [Tabular Data Augmentation for Machine Learning: Progress and Prospects of Embracing Generative AI](https://mlsanity.com/paper/2407.21523/) (2024)
- [AnaMeta: A Table Understanding Dataset of Field Metadata Knowledge Shared by Multi-dimensional Data Analysis Tasks](https://mlsanity.com/paper/2209.00946/) (2022)
- [Enhancing Temporal Understanding in LLMs for Semi-structured Tables](https://mlsanity.com/paper/2407.16030/) (2024)
- [Evaluating Concurrent Robustness of Language Models Across Diverse Challenge Sets](https://mlsanity.com/paper/2311.08662/) (2023)
- [Retrieval-Based Transformer for Table Augmentation](https://mlsanity.com/paper/2306.11843/) (2023)
- [Rows from Many Sources: Enriching row completions from Wikidata with a pre-trained Language Model](https://mlsanity.com/paper/2204.07014/) (2022)
- [Data augmentation with automated machine learning: approaches and performance comparison with classical data augmentation methods](https://mlsanity.com/paper/2403.08352/) (2024)

## Abstract (arXiv)

We address the task of auto-completing data cells in relational tables. Such tables describe entities (in rows) with their attributes (in columns). We present the CellAutoComplete framework to tackle several novel aspects of this problem, including: (i) enabling a cell to have multiple, possibly conflicting values, (ii) supplementing the predicted values with supporting evidence, (iii) combining evidence from multiple sources, and (iv) handling the case where a cell should be left empty. Our framework makes use of a large table corpus and a knowledge base as data sources, and consists of preprocessing, candidate value finding, and value ranking components. Using a purpose-built test collection, we show that our approach is 40% more effective than the best baseline.