# AutoChart: A Dataset for Chart-to-Text Generation Task

arXiv: https://arxiv.org/abs/2108.06897 · HTML: https://mlsanity.com/paper/2108.06897/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 25 references that are in the map.
- First posted on arXiv 16 Aug 2021.

## Builds on (most cited first, 12 of 12)

- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [PlotQA: Reasoning over Scientific Plots](https://mlsanity.com/paper/1909.00997/) (2019)
- [FigureQA: An Annotated Figure Dataset for Visual Reasoning](https://mlsanity.com/paper/1710.07300/) (2017)
- [Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation](https://mlsanity.com/paper/1703.09902/) (2017)
- [Data-to-Text Generation with Content Selection and Planning](https://mlsanity.com/paper/1809.00582/) (2018)
- [Chart-to-Text: Generating Natural Language Descriptions for Charts by Adapting the Transformer Model](https://mlsanity.com/paper/2010.09142/) (2020)
- [RankME: Reliable Human Ratings for Natural Language Generation](https://mlsanity.com/paper/1803.05928/) (2018)
- [Data Extraction from Charts via Single Deep Neural Network](https://mlsanity.com/paper/1906.11906/) (2019)
- [Chart-Text: A Fully Automated Chart Image Descriptor](https://mlsanity.com/paper/1812.10636/) (2018)
- [Beagle: Automated Extraction and Interpretation of Visualizations from the Web](https://mlsanity.com/paper/1711.05962/) (2017)
- [Learning to Select, Track, and Generate for Data-to-Text](https://mlsanity.com/paper/1907.09699/) (2019)
- [Scatteract: Automated extraction of data from scatter plots](https://mlsanity.com/paper/1704.06687/) (2017)

## Built on by (most cited first, 13 of 13)

- [ChartBench: A Benchmark for Complex Visual Reasoning in Charts](https://mlsanity.com/paper/2312.15915/) (2023)
- [ChartSumm: A Comprehensive Benchmark for Automatic Chart Summarization of Long and Short Summaries](https://mlsanity.com/paper/2304.13620/) (2023)
- [Text2Chart31: Instruction Tuning for Chart Generation with Automatic Feedback](https://mlsanity.com/paper/2410.04064/) (2024)
- [Summaries as Captions: Generating Figure Captions for Scientific Documents with Automated Text Summarization](https://mlsanity.com/paper/2302.12324/) (2023)
- [ChartCap: Mitigating Hallucination of Dense Chart Captioning](https://mlsanity.com/paper/2508.03164/) (2025)
- [Tackling Hallucinations in Neural Chart Summarization](https://mlsanity.com/paper/2308.00399/) (2023)
- [Chart-HQA: A Benchmark for Hypothetical Question Answering in Charts](https://mlsanity.com/paper/2503.04095/) (2025)
- [Faithful Chart Summarization with ChaTS-Pi](https://mlsanity.com/paper/2405.19094/) (2024)
- [AltChart: Enhancing VLM-based Chart Summarization Through Multi-Pretext Tasks](https://mlsanity.com/paper/2405.13580/) (2024)
- [Structuring the Unstructured: A Systematic Review of Text-to-Structure Generation for Agentic AI with a Universal Evaluation Framework](https://mlsanity.com/paper/2508.12257/) (2025)
- [Multimodal Information Fusion for Chart Understanding: A Survey of MLLMs -- Evolution, Limitations, and Cognitive Enhancement](https://mlsanity.com/paper/2602.10138/) (2026)
- [Semantic Segmentation of Node and Edge Diagrams for Assistive Technology](https://mlsanity.com/paper/2606.11320/) (2026)
- [Do you "see" what I "see"? A Multi-panel Visual Question Answer Dataset for Large Language Model Chart Analysis](https://mlsanity.com/paper/2610.14173/) (2026)

## Abstract (arXiv)

The analytical description of charts is an exciting and important research area with many applications in academia and industry. Yet, this challenging task has received limited attention from the computational linguistics research community. This paper proposes textsfAutoChart, a large dataset for the analytical description of charts, which aims to encourage more research into this important area. Specifically, we offer a novel framework that generates the charts and their analytical description automatically. We conducted extensive human and machine evaluations on the generated charts and descriptions and demonstrate that the generated texts are informative, coherent, and relevant to the corresponding charts.