FlowSense: A Natural Language Interface for Visual Data Exploration within a Dataflow System
This work addresses usability issues for users of dataflow visualization systems, though it is incremental as it applies existing NLP techniques to a specific domain.
The authors tackled the problem of high learning overhead in dataflow visualization systems by developing FlowSense, a natural language interface that assists in constructing dataflow diagrams, which was evaluated through a case study and user study to enhance usability.
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.