2026-09-19T05:24:43Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1512072023-08-01T03:02:48Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Satyanarayan, Arvind
Tang, Ben Jun-Hong
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
System Design and Management Program.
2023-07-31T19:22:39Z
2023-07-31T19:22:39Z
2023-06
2023-06-23T19:56:58.487Z
https://hdl.handle.net/1721.1/151207
0000-0001-9907-8008
Captions that describe or explain charts help improve recall and comprehension of the depicted data and provide a more accessible medium for people with visual disabilities. However, current approaches for automatically generating such captions struggle to articulate the perceptual or cognitive features that are the hallmark of charts (e.g., complex trends and patterns). In response, we introduce VisText: a dataset of 12,441 pairs of charts and captions that describe the charts’ construction, report key statistics, and identify perceptual and cognitive phenomena. In VisText, a chart is available as three representations: a rasterized image, a backing data table, and a scene graph — a hierarchical representation of a chart’s visual elements akin to a web page’s Document Object Model (DOM). To evaluate the impact of VisText, we fine-tune state-of-the-art language models on our chart captioning task and apply prefix-tuning to produce captions that vary the semantic content they convey. Our models generate coherent, semantically rich captions and perform on par with state-of-the-art chart captioning models across machine translation and text generation metrics. Through qualitative analysis, we identify six broad categories of errors that our models make that can inform future work.
S.M.
S.M.
Massachusetts Institute of Technology
In Copyright - Educational Use Permitted
Copyright retained by author(s)
https://rightsstatements.org/page/InC-EDU/1.0/
VisText: A Benchmark for Semantically Rich Chart Captioning
Thesis
application/pdf
Master
Master of Science in Electrical Engineering and Computer Science
Master of Science in Engineering and Management
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="f2590216-8467-4f6b-ba8c-84d8a8440d32">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>VisText: A Benchmark for Semantically Rich Chart Captioning</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2023-06</PublicationDate>
<Authors>
<Author>
<DisplayName>Tang, Ben Jun-Hong</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>https://rightsstatements.org/page/InC-EDU/1.0/</License>
<Abstract>Captions that describe or explain charts help improve recall and comprehension of the depicted data and provide a more accessible medium for people with visual disabilities. However, current approaches for automatically generating such captions struggle to articulate the perceptual or cognitive features that are the hallmark of charts (e.g., complex trends and patterns). In response, we introduce VisText: a dataset of 12,441 pairs of charts and captions that describe the charts’ construction, report key statistics, and identify perceptual and cognitive phenomena. In VisText, a chart is available as three representations: a rasterized image, a backing data table, and a scene graph — a hierarchical representation of a chart’s visual elements akin to a web page’s Document Object Model (DOM). To evaluate the impact of VisText, we fine-tune state-of-the-art language models on our chart captioning task and apply prefix-tuning to produce captions that vary the semantic content they convey. Our models generate coherent, semantically rich captions and perform on par with state-of-the-art chart captioning models across machine translation and text generation metrics. Through qualitative analysis, we identify six broad categories of errors that our models make that can inform future work.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>