CrossData: Leveraging Text-Data Connections for Authoring Data Documents

Chen, Zhutian; Xia, Haijun

doi:10.1145/3491102.3517485

Cited by 22 publications

(9 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…NLIs are widely studied as a promising means of interaction for visual analytics [1], [11]. NLIs for data visualization generate visual representations in response to NL queries, which help reveal data insights [12], [13], [14], [15], [16], [17], [18], [19]. Cox et al [20] aimed to integrate NLI into existing visualization systems.…”

Section: Related Work 21 Nli For Data Visualizationmentioning

confidence: 99%

See 1 more Smart Citation

XNLI: Explaining and Diagnosing NLI-Based Visual Data Analysis

Feng

Wang

Pan

et al. 2024

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

Natural language interfaces (NLIs) enable users to flexibly specify analytical intentions in data visualization. However, diagnosing the visualization results without understanding the underlying generation process is challenging. Our research explores how to provide explanations for NLIs to help users locate the problems and further revise the queries. We present XNLI, an explainable NLI system for visual data analysis. The system introduces a Provenance Generator to reveal the detailed process of visual transformations, a suite of interactive widgets to support error adjustments, and a Hint Generator to provide query revision hints based on the analysis of user queries and interactions. Two usage scenarios of XNLI and a user study verify the effectiveness and usability of the system. Results suggest that XNLI can significantly enhance task accuracy without interrupting the NLI-based analysis process.

show abstract

Section: Related Work 21 Nli For Data Visualizationmentioning

confidence: 99%

“…Each aspect of the visualization process is specified according to the original query. These potential connections constructed by NLI [16] are usually inaccessible to the users. P1 and P5 commented that they wondered how their queries were parsed by the system, especially when obtaining unexpected results.…”

Section: Design Requirementsmentioning

confidence: 99%

XNLI: Explaining and Diagnosing NLI-Based Visual Data Analysis

Feng

Wang

Pan

et al. 2024

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

show abstract

“…On the other hand, implicit NLI systems view the text descriptions as another representation of the visual content, automatically converting the text to visual content and thus enabling users to create visual content implicitly. Extensive research in computer vision, computer graphics, and human-computer interaction has explored the automatic conversion of descriptive text into visual content, such as images [72,73], 3D shapes [9] and scenes [8,15], documents [11], and short video clips [35]. In recent years, with the development of generative adversarial networks, a plethora of systems [32,69,74,76,77] have been proposed to generate visual content based on text descriptions.…”

Section: Related Workmentioning

confidence: 99%

Sporthesia: Augmenting Sports Videos Using Natural Language

Chen

Yang

Xie

et al. 2023

IEEE Trans. Visual. Comput. Graphics

Self Cite

View full text Add to dashboard Cite

SporthesiaVideo Processor "…gets him close to the backhand court" Video Commentary "Federer looks to be covering the crosscourt, which gets him close to the backhand court. " + "Feder looks to be covering the crosscourt…" a b cFig. 1: Sporthesia takes raw video footage and commentary text of racket-based sports as input, and outputs an augmented video. To achieve this, three key steps are taken: 1) detecting the visualizable entities in the text, 2) mapping the entities to visualizations, and 3) scheduling the visualizations to play with the raw video.

show abstract

“…CrossData [45] identifies relationships between a writer's prose and embedded tables and charts -automatically extracting data values and allowing writers to explore alternative properties. CrossData identifies parameters and values in prose automatically using NLP techniques, whereas in our work we ask users to identify parameters themselves.…”

Section: F Natural Language and Datamentioning

confidence: 99%

“…on the page in Figure 4 and selected "Apple" as a parameter, they might want the algorithm to infer that "Banana", "Pineapple", and "Fig" are alternative values. Our algorithm first builds an XPath 45 query that uniquely matches the element. It builds an index-based XPath (e.g., not classes alone) since this is the easiest way to ensure a unique XPath.…”

Section: Refining An Automation Macro To Support Edge Casesmentioning

confidence: 99%

ParamMacros: Creating UI Automation Leveraging End-User Natural Language Parameterization

Krosnick

Oney

2022

2022 IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC)

View full text Add to dashboard Cite

Prior work in programming-by-demonstration (PBD) has explored ways to enable end-users to create custom automation without needing to write code. We propose a new end-user specification model -asking the end-user to explicitly identify parts of their natural language query that can be generalized. We built a PBD system, ParamMacros, where users first generalize a concrete natural language question -identifying parameters and their possible values -and then create a demonstration of how to answer the question on the website of interest. ParamMacros then infers a generalized program by using the user-provided parameter values to identify relevant patterns in the website's structure. In a lab study we found that participants were able to meaningfully parameterize natural language queries and felt such a parameterization and demonstration process would be useful for creating custom automation.

show abstract

CrossData: Leveraging Text-Data Connections for Authoring Data Documents

Cited by 22 publications

References 53 publications

XNLI: Explaining and Diagnosing NLI-Based Visual Data Analysis

XNLI: Explaining and Diagnosing NLI-Based Visual Data Analysis

Sporthesia: Augmenting Sports Videos Using Natural Language

ParamMacros: Creating UI Automation Leveraging End-User Natural Language Parameterization

Contact Info

Product

Resources

About