Chart Question Answering

17 papers with code • 3 benchmarks • 8 datasets

Question Answering task on charts images

Libraries

Use these libraries to find Chart Question Answering models and implementations

Most implemented papers

Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding

google-research/pix2struct 7 Oct 2022

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 29 May 2023

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.

ScreenAI: A Vision-Language Model for UI and Infographics Understanding

google-research-datasets/screen_qa 7 Feb 2024

At the heart of this mixture is a novel screen annotation task in which the model has to identify the type and location of UI elements.

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

kushalkafle/DVQA_dataset CVPR 2018

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

kushalkafle/PREFIL 5 Aug 2019

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 29 Nov 2021

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

huggingface/transformers 19 Dec 2022

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

huggingface/transformers 20 Dec 2022

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.