Issues in realizing the overall message of a bar chart

Demir, Şeniz; Carberry, Sandra; Elzer, Stephanie

doi:10.1075/cilt.309.26dem

Cited by 3 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For each graphic, we used our approach to generate the referring expression for the dependent axis. Finally, the resultant output and three baselines were evaluated by two evaluators (Demir, Carberry, and Elzer 2009). The evaluation results showed that our approach performs much better than any of the baselines for the 205 graphics in the corpus.…”

Section: Methodsmentioning

confidence: 99%

“…We undertook a corpus study in order to identify how a measurement axis descriptor could be generated from the text of a graphic; the results of the analysis form the basis for the heuristics and augmentation rules we developed for generating the measurement axis descriptor for a graphic. In Demir, Carberry, and Elzer (2009), we outlined this problem as generating a graphical element required for realizing the intended message of a graphic and thoroughly described the technical details of our approach. Here, however, we treat this particular aspect as a novel text-to-text generation methodology which is combined with other data-to-text approaches in a complete NLG system.…”

Section: Measurement Axis Descriptormentioning

confidence: 99%

See 1 more Smart Citation

Summarizing Information Graphics Textually

Demir

Carberry

McCoy

2012

Computational Linguistics

Self Cite

View full text Add to dashboard Cite

Information graphics (such as bar charts and line graphs) play a vital role in many multimodal documents. The majority of information graphics that appear in popular media are intended to convey a message and the graphic designer uses deliberate communicative signals in order to bring that message out such as highlighting certain aspects of the graphic. The graphic, whose communicative goal (intended message) is often not captured by the document's accompanying text, contributes to the overall purpose of the document and cannot be ignored. This article presents our approach to providing the high-level content of a non-scientific information graphic via a brief textual summary which includes the intended message and the salient features of the graphic. This work brings together insights obtained from empirical studies in order to determine what should be contained in the summaries of this form of non-linguistic input data, and how the information required for realizing the selected content can be extracted from the visual image and the textual components of the graphic. This work also presents a novel bottom-up generation approach to simultaneously construct the discourse and sentence structures of textual summaries by leveraging different discourse related considerations such as the syntactic complexity of realized sentences and clause embeddings. The effectiveness of our work was validated by different evaluation studies.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Measurement Axis Descriptormentioning

confidence: 99%

Summarizing Information Graphics Textually

Demir

Carberry

McCoy

2012

Computational Linguistics

Self Cite

View full text Add to dashboard Cite

show abstract

“…The XML representation 1 http://ir.cis.udel.edu/~moraes/udgraphs of the graphic, along with the intended message identified by the IRM, is sent to the Generation Module (GM), which produces a textual summary of the most important content presented in the graphic. The system produces an initial summary and follow-up responses for simple bar charts (Demir, Carberry, & Elzer, 2009;Demir, Carberry, & McCoy, 2008) and this demo presents the GM for simple line graphs.…”

Section: Introductionmentioning

confidence: 99%

Generating Summaries of Line Graphs

Moraes

Sina

McCoy

et al. 2014

Proceedings of the 8th International Natural Language Generation Conference (INLG)

Self Cite

View full text Add to dashboard Cite

This demo presents a Natural Language Generation (NLG) system that generates summaries of informational graphics, specifically simple line graphs, present in popular media. The system is intended to capture the high-level knowledge conveyed by the graphic and its outstanding visual features. It comprises a content selection phase that extracts the most important content of the graphic, an organization phase, which orders the propositions in a coherent manner, and a realization phase that uses the text surrounding the article to make decisions on the choice of lexical items and amount of aggregation applied to the propositions to generate the summary of the graphic.

show abstract