ML4VIZ : 시각화를 위한 머신러닝 연구 동향

Data wrangling is the process of cleaning, structuring and enriching raw data into a desired format for better decision making in less time. Data wrangling is increasingly ubiquitous at today's top firms. Data has become more diverse and unstructured, demanding increased time spent culling, cleaning, and organizing data ahead of broader analysis.

Visualization recommender systems aim to lower the barrier to exploring basic visualizations by automatically generating results for analysts to search and select, rather than manually specify. Here, we demonstrate a novel machine learning-based approach to visualization recommendation that learns visualization design choices from a large corpus of datasets and associated visualizations.

Information graphics (infographics) can effectively deliver messages in an engaging and memorable fashion. Hence, they have now gained tremendous popularity in presentations, documents, dashboards, etc. However, as a task usually requiring high-level design creativity and good proficiency with graphic design tools, authoring a professional infographic remains a challenge for information workers.

Identifying trendline visualizations with desired patterns is a common and fundamental data exploration task. Existing visual analytics tools offer limited flexibility and expressiveness for such tasks, especially when the pattern of interest is under-specified and approximate, and do not scale well when the pattern searching needs are ad-hoc, as is often the case.

Bar charts are an effective way to convey numeric information, but today's algorithms cannot parse them. Existing methods fail when faced with even minor variations in appearance. Here, we present DVQA, a dataset that tests many aspects of bar chart understanding in a question answering framework.

Image captioning transforms complex visual information into abstract natural language for representation, which can help computers understanding the world quickly. However, due to the complexity of the real environment, it needs to identify key objects and realize their connections, and further generate natural language.