Chart Question Answering
16 papers with code • 3 benchmarks • 8 datasets
Question Answering task on charts images
Benchmarks
These leaderboards are used to track progress in Chart Question Answering
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
Libraries
Use these libraries to find Chart Question Answering models and implementations
ChartQA
DVQA
PlotQA
LEAF-QA
RealCQA
Vega-Lite Chart Collection
Most implemented papers
Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding
google-research/pix2struct
•
•
Visually-situated language is ubiquitous -- sources range from textbooks with diagrams to web pages with images and tables, to mobile apps with buttons and forms.
PaLI-X: On Scaling up a Multilingual Vision and Language Model
kyegomez/PALI
•
•
We present the training recipe and results of scaling up PaLI-X, a multilingual vision and language model, both in terms of size of the components and the breadth of its training task mixture.
FigureQA: An Annotated Figure Dataset for Visual Reasoning
vmichals/FigureQA-baseline
•
•
ICLR 2018
To resolve, such questions often require reference to multiple plot elements and synthesis of information distributed spatially throughout a figure.
DVQA: Understanding Data Visualizations via Question Answering
Bar charts are an effective way to convey numeric information, but today's algorithms cannot parse them.
Answering Questions about Data Visualizations using Efficient Bimodal Fusion
Chart question answering (CQA) is a newly proposed visual question answering (VQA) task where an algorithm must answer questions about data visualizations, e. g. bar charts, pie charts, and line graphs.
Classification-Regression for Chart Comprehension
levymsn/cqa-crct
•
•
Our model is particularly well suited for realistic questions with out-of-vocabulary answers that require regression.
ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning
vis-nlp/chartqa
•
•
Findings (ACL) 2022
To address the unique challenges in our benchmark involving visual and logical reasoning over charts, we present two transformer-based models that combine visual features and the data table of the chart in a unified way to answer questions.
MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering
Visual language data such as plots, charts, and infographics are ubiquitous in the human world.
DePlot: One-shot visual language reasoning by plot-to-table translation
Compared with a SOTA model finetuned on more than >28k data points, DePlot+LLM with just one-shot prompting achieves a 24. 0% improvement over finetuned SOTA on human-written queries from the task of chart QA.
UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning
vis-nlp/unichart
•
•
Charts are very popular for analyzing data, visualizing key insights and answering complex reasoning questions about data.
