Workshop themes
Theme 1: Integrating text with charts
In the field of data visualization, it is natural that the focus is on examining and implementing best practices for generating charts and graphics. However, it remains important to also factor in the context in which visualizations and graphics appear. When integrating visualization with text, the textual component is often either overlooked or at least undervalued when exploring novel ways of communicating through data. Research in natural language generation (NLG) has made tremendous progress, with algorithms now being able to translate text, summarize articles, and describe imagery with high accuracy. As a result, a growing number of interfaces and tools are incorporating NLG techniques to help readers interpret visualizations and aid data-driven communication, ranging from creating captions, narratives, stories, or describe takeaways from a chart or dashboard. NLG can also make data more accessible to more people by providing textual descriptions and interpretation. However, the use of NLG techniques in the context of information visualization is relatively nascent both in terms of utility and generalizability.
The first theme in this workshop will focus on ways to better understand the importance and role of text in information visualization.
Theme 2: Natural language interaction for visual analysis
Natural language interfaces (NLIs) have been the “holy grail” of human-computer interaction and information search for decades. Early attempts in building NLIs to query databases achieved limited success due to challenges in language understanding capability. Recent years have seen a resurgence of NLIs in the form of dialog systems, semantic parsing, question-answering systems, as well as smart assistants. The focus of such systems is understanding user intent, identifying ambiguity, and providing ways for users to refine and repair the system as they converse with it. NLIs for visualization are gaining popularity both within academic research and are being adopted in mainstream commercial visual analysis tools. However, many open questions still persist regarding both the interpretation of language input and the interface and interaction design within these systems.
The second theme of this workshop focuses on improving people’s ability to engage with data and visualizations through language-based interfaces.
Theme 3: Enhancing data semantics with NLP techniques
NLP techniques (e.g., sentiment analysis, entity classification, topic modeling) have traditionally been used to facilitate the analysis of textual data for scenarios such as investigative analysis, political speech/debate summarization, and social media content analysis, among others. However, NLP algorithms also present an opportunity for systems to understand the semantics of an input dataset (e.g., detecting geographic locations, people names, or specific types of date strings). This semantic enrichment can be used for richer data summaries, automatic defaults in visual analytics tools, and richer data exploration. While intriguing in theory, the application of semantics toward richer analytical experiences is still an under-explored idea.
The third theme of the workshop will delve into text visualization systems and approaches to add semantics as part of the
visual analysis process.