NL2INTERFACE: Interactive Visualization Interface Generation from Natural Language Queries
Preprint
Abstract
We develop NL2INTERFACE to explore the potential of generating usable interactive multi-visualization interfaces from natural language queries. With NL2INTERFACE, users can directly write natural language queries to automatically generate a fully interactive multi-visualization interface without any extra effort of learning a tool or programming language. Further, users can interact with the interfaces to easily transform the data and quickly see the results in the visualizations.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Demonstration of PI2: Interactive Visualization Interface Generation for SQL Analysis in Notebook2022
- Natural SQL: Making SQL Easier to Infer from Natural Language Specifications2021
- PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models2021
- Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?2021
- NL4DV: A Toolkit for Generating Analytic Specifications for Data Visualization from Natural Language QueriesIEEE Transactions on Visualization and Computer Graphics, 2020
- RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers2020
- Precision Interfaces for Different Modalities2018
- Applying Pragmatics Principles for Interaction with Visual AnalyticsIEEE Transactions on Visualization and Computer Graphics, 2017
- Show Me: Automatic Presentation for Visual AnalysisIEEE Transactions on Visualization and Computer Graphics, 2007
- A Multi-Modal Natural Language Interface to an Information Visualization EnvironmentInternational Journal of Speech Technology, 2001