An interactive visualization method of numerical data based on natural language requirements

Authors:
Mitsunori Matsushita;Eisaku Maeda;Tsuneaki Kato
Affiliations:
NTT Communication Science Labs., NTT Corp. 2-4 Hikaridai, Seikacho, Sorakugun, Kyoto 619-0237, Japan;NTT Communication Science Labs., NTT Corp. 2-4 Hikaridai, Seikacho, Sorakugun, Kyoto 619-0237, Japan;Graduate School of Arts and Sciences, University of Tokyo, 3-8-1 Komaba, Meguroku, Tokyo 153-8902, Japan
Venue:
International Journal of Human-Computer Studies - Special issue on HCI research in Japan
Year:
2004

Citing 16
Cited 0

Automating the design of graphical presentations of relational information

ACM Transactions on Graphics (TOG)
Data characterization for intelligent graphics presentation

CHI '90 Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Task-analytic approach to the automated design of graphic presentations

ACM Transactions on Graphics (TOG)
The cost-of-knowledge characteristic function: display evaluation for direct-walk dynamic information visualizations

CHI '94 Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Visual information seeking: tight coupling of dynamic query filters with starfield displays

CHI '94 Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
The table lens: merging graphical and symbolic representations in an interactive focus + context visualization for tabular information

CHI '94 Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Readings in information visualization: using vision to think

Readings in information visualization: using vision to think
Developing a natural language interface to complex data

ACM Transactions on Database Systems (TODS)
Mapping communicative goals into conceptual tasks to generate graphics in discourse

Proceedings of the 5th international conference on Intelligent user interfaces
ConMan: a visual programming language for interactive graphics

SIGGRAPH '88 Proceedings of the 15th annual conference on Computer graphics and interactive techniques
DataGuides: Enabling Query Formulation and Optimization in Semistructured Databases

VLDB '97 Proceedings of the 23rd International Conference on Very Large Data Bases
IVEE: an Information Visualization and Exploration Environment

INFOVIS '95 Proceedings of the 1995 IEEE Symposium on Information Visualization
Efficient Multi-Object Dynamic Query Histograms

INFOVIS '99 Proceedings of the 1999 IEEE Symposium on Information Visualization
Recovery strategies for parsing extragrammatical language

Computational Linguistics - Special issue on ill-formed input
Criteria to choose appropriate graph-types

PRICAI'00 Proceedings of the 6th Pacific Rim international conference on Artificial intelligence
Visual prompts and graphical design: a framework for exploring the design space of 2-D charts and graphs

AAAI'97/IAAI'97 Proceedings of the fourteenth national conference on artificial intelligence and ninth conference on Innovative applications of artificial intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes an interactive visualization method to support the exploration of data in decision-making and problem solving. Since this method employs an asymmetric communication mode, i.e. taking queries and requests expressed in a natural language as input and answering them with statistical charts, it can convert the normally tedious repetitive human-computer interaction into a felicitous dialogue. This is because the natural language interface allows users to articulate their requests directly and intuitively, and charts and graphics have many benefits when analysing a large amount of data in order to determine overall characteristics or to resolve user questions. The proposed method resolves the conundrum that the appropriateness of a chart depends on the context. In this method, two factors are considered in choosing chart type so as to satisfy the user requirement represented in a natural language: the type of chart displayed and the type of user utterance. Our proposed method allows the data to be visualized interactively to match the changes in the user's viewpoint without interrupting the thinking process.