Datatone: Managing ambiguity in natural language interfaces for data visualization

Tong Gao, Mira Dontcheva, Eytan Adar, Zhicheng Liu, Karrie Karahalios

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Answering questions with data is a difficult and time-consuming process. Visual dashboards and templates make it easy to get started, but asking more sophisticated questions often requires learning a tool designed for expert analysts. Natural language interaction allows users to ask questions directly in complex programs without having to learn how to use an interface. However, natural language is often ambiguous. In this work we propose a mixed-initiative approach to managing ambiguity in natural language interfaces for data visualization. We model ambiguity throughout the process of turning a natural language query into a visualization and use algorithmic disambiguation coupled with interactive ambiguity widgets. These widgets allow the user to resolve ambiguities by surfacing system decisions at the point where the ambiguity matters. Corrections are stored as constraints and influence subsequent queries. We have implemented these ideas in a system, DataTone. In a comparative study, we find that DataTone is easy to learn and lets users ask questions without worrying about syntax and proper question form.

Original languageEnglish (US)
Title of host publicationUIST 2015 - Proceedings of the 28th Annual ACM Symposium on User Interface Software and Technology
PublisherAssociation for Computing Machinery, Inc
Pages489-500
Number of pages12
ISBN (Electronic)9781450337793
DOIs
StatePublished - Nov 5 2015
Event28th Annual ACM Symposium on User Interface Software and Technology, UIST 2015 - Charlotte, United States
Duration: Nov 8 2015Nov 11 2015

Publication series

NameUIST 2015 - Proceedings of the 28th Annual ACM Symposium on User Interface Software and Technology

Other

Other28th Annual ACM Symposium on User Interface Software and Technology, UIST 2015
CountryUnited States
CityCharlotte
Period11/8/1511/11/15

Keywords

  • Mixed-initiative interfaces
  • Natural language interaction
  • Visualization

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Datatone: Managing ambiguity in natural language interfaces for data visualization'. Together they form a unique fingerprint.

  • Cite this

    Gao, T., Dontcheva, M., Adar, E., Liu, Z., & Karahalios, K. (2015). Datatone: Managing ambiguity in natural language interfaces for data visualization. In UIST 2015 - Proceedings of the 28th Annual ACM Symposium on User Interface Software and Technology (pp. 489-500). (UIST 2015 - Proceedings of the 28th Annual ACM Symposium on User Interface Software and Technology). Association for Computing Machinery, Inc. https://doi.org/10.1145/2807442.2807478