Textual Analogy Parsing: What's Shared and What's Compared among Analogous Facts

Lamm, Matthew; Chaganty, Arun Tejasvi; Manning, Christopher D.; Jurafsky, Dan; Liang, Percy

doi:10.48550/arxiv.1809.02700

Cited by 2 publications

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For sequence tagging techniques, rule-based methods [52] are straightforward, but costly and limited. There are also many machine learning methods proposed which are more robust and easier to generalize, including Hidden Markov Models (HMM) [9], Support Vector Machines (SVM) [4] and Conditional Random Fields (CRF) [34].…”

Section: Natural Language Interactionsmentioning

confidence: 99%

Text-to-Viz: Automatic Generation of Infographics from Proportion-Related Natural Language Statements

Cui

Zhang

Wang

et al. 2020

IEEE Trans. Visual. Comput. Graphics

110

View full text Add to dashboard Cite

Figure 1. Examples created by Text-to-Viz. (a)-(d) are generated from the statement: "More than 20% of smartphone users are social network users." (e) and (f) are generated from the statement: "40 percent of USA freshwater is for agriculture." (g) and (h) are generated from the statement: "3 in 5 Chinese people live in rural areas." (i) and (j) are generated from the statement: "65% of coffee is consumed at breakfast." (k)-(m) are generated from the statement: "Among all students, 49% like football, 32% like basketball, and 21% like baseball." (n) and (o) are generated from the statement: "Humans made 51.5% of online traffic, while good bots made 19.5% and bad bots made 29%."Abstract-Combining data content with visual embellishments, infographics can effectively deliver messages in an engaging and memorable manner. Various authoring tools have been proposed to facilitate the creation of infographics. However, creating a professional infographic with these authoring tools is still not an easy task, requiring much time and design expertise. Therefore, these tools are generally not attractive to casual users, who are either unwilling to take time to learn the tools or lacking in proper design expertise to create a professional infographic. In this paper, we explore an alternative approach: to automatically generate infographics from natural language statements. We first conducted a preliminary study to explore the design space of infographics. Based on the preliminary study, we built a proof-of-concept system that automatically converts statements about simple proportionrelated statistics to a set of infographics with pre-designed styles. Finally, we demonstrated the usability and usefulness of the system through sample results, exhibits, and expert reviews.

show abstract

Section: Natural Language Interactionsmentioning

confidence: 99%

Text-to-Viz: Automatic Generation of Infographics from Proportion-Related Natural Language Statements

Cui

Zhang

Wang

et al. 2020

IEEE Trans. Visual. Comput. Graphics

110

View full text Add to dashboard Cite

show abstract

“…Last, NLP could automatize the extraction of labels by parsing the relation between the number and the label. Such a system could draw from approaches to parse textual analogies [36,77]. However, these remain challenging even with modern techniques (see the difficulties faced by approaches to automatically connect text and chart [76,113]).…”

Section: Future Workmentioning

confidence: 99%

Charagraph: Interactive Generation of Charts for Realtime Annotation of Data-Rich Paragraphs

Masson

Malacria

Casiez

et al. 2023

Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

□ □ (p < .0 (p < □ , □ ms) (c) Select data-group (b) Delimit selection (a) Document with Charagraphs (d) Identify (e) Compare Creation Interaction Figure 1: (a) Charagraphs are in-situ visualizations of numeric data included within text that are dynamically generated (b) by delimiting a selection and (c) selecting a data group. Charagraphs support common data exploration tasks through interactive features such as (d) identifying and (e) comparing values.

show abstract

Textual Analogy Parsing: What's Shared and What's Compared among Analogous Facts

Cited by 2 publications

References 26 publications

Text-to-Viz: Automatic Generation of Infographics from Proportion-Related Natural Language Statements

Text-to-Viz: Automatic Generation of Infographics from Proportion-Related Natural Language Statements

Charagraph: Interactive Generation of Charts for Realtime Annotation of Data-Rich Paragraphs

Contact Info

Product

Resources

About