自然语言和可视化(Vis)是人类沟通的两种强大方式。本教程的目标是推动紧密整合这两种方式的议程。为此,本教程将介绍NLP+Vis,重点关注两个主要的工作方向: NLP用于Vis:如何开发和调整最先进的NLP模型以解决各种可视化任务? Vis用于NLP:如何利用可视化技术有效地解释和解释复杂的NLP模型? 本教程将首先阐述为什么NLP+Vis是一个重要的研究领域,并概述结合NLP和Vis技术的研究主题。然后将介绍最先进的深度学习模型在NLP领域的应用概况。接下来,我们将提供一览可视化技术在使NLP模型可解释和可解释方面的应用。在最后一部分,我们将关注NLP和Vis交叉领域的各种应用任务。最后,我们将进行互动讨论,探讨NLP+Vis应用的未来挑战。受众包括对将NLP应用于可视化感兴趣的研究人员,以及那些更广泛关注机器学习和可视化交叉领域的人。
What is NLP? * What is Vis? * Why NLP+Vis? * An overview of research topics on combining NLP and Vis techniques * An overview of the tutorial
Encoder-decoder model * Attention mechanism * Transformer architecture * Language modeling and LLMs (e.g., BERT, T5, GPT) * Multi-modal learning (image, text, tables) * Huggingface library (time permitting)
Intro to vis for interpretability * Vis tools and use cases * Challenges and limitations
Visual text analytics * Natural language interfaces for visualizations * ChartNLP (e.g., Chart question answering, Text2Chart) * Natural language generation for visualization * Automated data-driven storytelling * NLP for chart accessibility * NLP+Vis for inclusions (e.g., promote visualization Literacy)
Building benchmarks for training and evaluation * Data annotation challenges * Emerging applications