A Browser Extension for Providing Visually Impaired Users Access to the Content of Bar Charts on the Web

Elzer, Stephanie; Schwartz, Edward J.; Carberry, Sandra; Chester, Daniel; Demir, Şeniz; Wu, Peng

doi:10.5220/0001274600590066

Cited by 10 publications

(1 citation statement)

References 14 publications

(11 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The task of generating a summary to accompany a chart is an instance of data-to-text generation and has a long tradition in natural language generation (NLG) (Elzer et al, 2007;Ferres et al, 2007;Demir et al, 2012). Recent neural models for chart summarization (Obeid and Hoque, 2020;Hsu et al, 2021;Zhu et al, 2021;Kantharaj et al, 2022) carry the promise to be trainable from data and hence more versatile than approaches using manually constructed templates, and to produce more fluent text than previous statistical NLG systems.…”

Section: Introductionmentioning

confidence: 99%

Tackling Hallucinations in Neural Chart Summarization

Obaid ul Islam,

Škrjanec,

Dusek

et al. 2023

Proceedings of the 16th International Natural Language Generation Conference

View full text Add to dashboard Cite

Hallucinations in text generation occur when the system produces text that is not grounded in the input. In this work, we tackle the problem of hallucinations in neural chart summarization. Our analysis shows that the target side of chart summarization training datasets often contains additional information, leading to hallucinations. We propose a natural language inference (NLI) based method to preprocess the training data and show through human evaluation that our method significantly reduces hallucinations. We also found that shortening long-distance dependencies in the input sequence and adding chart-related information like title and legends improves the overall performance.

show abstract

Section: Introductionmentioning

confidence: 99%

Tackling Hallucinations in Neural Chart Summarization

Obaid ul Islam,

Škrjanec,

Dusek

et al. 2023

Proceedings of the 16th International Natural Language Generation Conference

View full text Add to dashboard Cite

show abstract

Issues in realizing the overall message of a bar chart

Demir¹,

Carberry²,

Elzer³

2009

Current Issues in Linguistic Theory

View full text Add to dashboard Cite

Information graphics, such as bar charts and line graphs, that appear in popular media generally have a message that they are intended to convey. We have developed a Bayesian network that recognizes the overall message of a bar chart and produces the logical representation of that message. However, the realization of a logical representation in natural language requires constructing referents for certain graphical elements. This chapter presents our solution to one aspect of this problem: identifying an appropriate referent for the dependent axis. An evaluation study validates our methodology and shows that it is much better than several baseline strategies.

show abstract

Accessible Visualization: Design Space, Opportunities, and Challenges

Kim

Joyner

Riegelhuth

et al. 2021

Computer Graphics Forum

View full text Add to dashboard Cite

Visualizations are now widely used across disciplines to understand and communicate data. The benefit of visualizations lies in leveraging our natural visual perception. However, the sole dependency on vision can produce unintended discrimination against people with visual impairments. While the visualization field has seen enormous growth in recent years, supporting people with disabilities is much less explored. In this work, we examine approaches to support this marginalized user group, focusing on visual disabilities. We collected and analyzed papers published for the last 20 years on visualization accessibility. We mapped a design space for accessible visualization that includes seven dimensions: user group, literacy task, chart type, interaction, information granularity, sensory modality, assistive technology. We described the current knowledge gap in light of the latest advances in visualization and presented a preliminary accessibility model by synthesizing findings from existing research. Finally, we reflected on the dimensions and discussed opportunities and challenges for future research.

show abstract

A Browser Extension for Providing Visually Impaired Users Access to the Content of Bar Charts on the Web

Cited by 10 publications

References 14 publications

Tackling Hallucinations in Neural Chart Summarization

Tackling Hallucinations in Neural Chart Summarization

Issues in realizing the overall message of a bar chart

Accessible Visualization: Design Space, Opportunities, and Challenges

Contact Info

Product

Resources

About