Neural Data-Driven Captioning of Time-Series Line Charts
Andrea Spreafico, Giuseppe Carenini
Abstract
The success of neural methods for image captioning suggests that similar benefits can be reaped for generating captions for information visualizations. In this preliminary study, we focus on the very popular line charts. We propose a neural model which aims to generate text from the same data used to create a line chart. Due to the lack of suitable training corpora, we collected a dataset through crowdsourcing. Experiments indicate that our model outperforms relatively simple non-neural baselines.
Topics & Concepts
Closed captioningComputer scienceCrowdsourcingFocus (optics)ChartLine (geometry)Artificial intelligenceNatural language processingTime seriesSeries (stratigraphy)Simple (philosophy)Artificial neural networkMachine learningInformation retrievalData miningSpeech recognitionImage (mathematics)World Wide WebPhysicsMathematicsStatisticsPhilosophyGeometryEpistemologyBiologyPaleontologyOpticsVideo Analysis and SummarizationMultimodal Machine Learning ApplicationsAdvanced Image and Video Retrieval Techniques