# FlowSense: A Natural Language Interface for Visual Data Exploration within a Dataflow System

## TL;DR

FlowSense introduces a natural language interface for dataflow visualization systems, enabling users to construct and modify dataflow diagrams more easily using plain English, thus reducing learning overhead.

## Contribution

It presents a novel NLP-based interface with semantic parsing and utterance tagging for flexible dataflow diagram construction in visualization systems.

## Key findings

- Improved usability in VisFlow with natural language commands
- Successful case study with domain experts on real data
- Positive results in formal user study

## Abstract

Dataflow visualization systems enable flexible visual data exploration by allowing the user to construct a dataflow diagram that composes query and visualization modules to specify system functionality. However learning dataflow diagram usage presents overhead that often discourages the user. In this work we design FlowSense, a natural language interface for dataflow visualization systems that utilizes state-of-the-art natural language processing techniques to assist dataflow diagram construction. FlowSense employs a semantic parser with special utterance tagging and special utterance placeholders to generalize to different datasets and dataflow diagrams. It explicitly presents recognized dataset and diagram special utterances to the user for dataflow context awareness. With FlowSense the user can expand and adjust dataflow diagrams more conveniently via plain English. We apply FlowSense to the VisFlow subset-flow visualization system to enhance its usability. We evaluate FlowSense by one case study with domain experts on a real-world data analysis problem and a formal user study.