The AAAI-21 Workshop on Content Authoring and Design (CAD21)

The AAAI-21
Workshop on Content Authoring and Design (CAD21)

In visual communication, a wide range of design components are typically used to increase the comprehension of content and to convey the author’s intent. Different authoring and graphic design applications perform automatic design assistance that include images and text in different forms and shapes. However, a majority of publicly available tools are mainly driven by some basic heuristics in assisting users during authoring. Recent works in the area started to employ AI-based models to assist users during authoring by recommending appropriate design components based on the content. Considering a wide range of applications, and their unique challenges, this interdisciplinary area hasn’t been fully studied and has little cross-disciplinary collaboration.

Our workshop focuses on the design aspect of any kind of content, including but is not limited to articles, news, social media posts, presentation slides, flyers, posters, and advertisement. This will be the first workshop on AI-assisted design and authoring.  The goal of the Content Authoring and Design workshop at AAAI is to engage the AI and NLP community around the open problems in authoring, reformatting, optimization, enhancement and beautification of different forms of contents from articles, news, presentation slides, flyers, posters to any material one can find online such as social media posts and advertisement. Content Authoring and Design refers to the interdisciplinary research space of Artificial Intelligence, Computational Linguistics, and Graphic Design. The area addresses open problems in leveraging AI-empowered models to assist users during creation by estimating the author/audience needs so that the outcome is aesthetically appealing and effectively communicates its intent.

Research related to the scope of the problem is emerging and thus the workshop will allow researchers interested in this area, and those already engaged in the topic to come together and share recent work. As an outcome of the workshop, new AI application tasks will be introduced to the community as well as state-of-the-art ML techniques and data resources. We plan to publish a survey paper describing the insights gained from the submissions. The workshop program will also include a shared task focused on “Predicting Emphasis in Presentation Slides”. This shared task builds on our recent SemEval 2020 shared task on “Emphasis Selection in short texts”, which attracted 197 participants and received submissions from 31 teams. Unlike most existing works on slide generation, the shared task emphasizes on the design aspect of presentation slides and efforts to automate the task.

CAD21 Program

Date: February 8

(schedule updated: 8 Jan)
Time zone: [PT, UTC-8]


The goal of the workshop is to gather insights from Artificial Intelligence, Computational Linguistics, Graphic Design and Creativity, Marketing Science, E-learning, as well as Social Media Analysis for content presentation enhancement, specifically, user-generated content, text in online marketing and education.

We invite thought-provoking submissions on topics including (but not limited to) text and multimedia content analysis, AI-assisted content authoring and design, understanding of congruent or user-friendly design, applications of design-based language processing, User-subjective approaches, Marketing, and brand alignment. Specific topics in this field include:

This research space is highly interdisciplinary. The study of the interrelationships between the computational analysis of content (text and language, in particular) and their applications in design is a recent and open research area.


Shared Task: Presentation Slides Emphasis Selection

We propose a new shared task where participants will expected to design automated approaches to predict emphasis in presentation slides with the goal of improving their comprehensibility and visual appeal. This shared task builds on our recent SemEval 2020 shared task on “Task 10: Emphasis Selection For Written Text in Visual Media.

CAD21@AAAI Codalab:

Shared task Dates


We will hold a 1-day workshop where approximately two-thirds of the time will be devoted to presentations of regular workshop submissions and an invited talk. The rest of the day will be devoted to the shared task overview and papers.

We encourage 2 types of submissions: archival submission of novel and unpublished work, and non-archival submissions that present recently published work.

Archival submissions:

Submissions should report original and unpublished research on topics of interest to the workshop. Accepted papers are expected to be presented at the workshop and will be published in the workshop proceedings. Archival submissions accepted for presentation at the workshop must not be or have been presented at any other meeting with publicly available proceedings.

Non-archival submissions:

We welcome submissions of a one-page abstract describing work recently published but that is of relevance to the topics of the workshop. The goal is to increase the visibility of work in this emerging area and facilitate researchers and practitioners with common research interests to meet each other and learn about efforts in this space.

We welcome long (up to 8 pages), short (up to 4 pages) and one-page abstracts. Long/short paper submissions must use the AAAI official templates. More information about submission formatting can be found here

Submission website:

Submission Dates

Keynote Speakers

- Aaron Hertzmann

Can Computers Create Art?

I will discuss whether computers, using Artificial Intelligence (AI), could create art. I cover the history of automation in art, examining the hype and reality of AI tools for art together with predictions about how they will be used. I will also discuss different scenarios for how an algorithm could be considered the author of an artwork, which, I argue, comes down to questions of why we create and appreciate artwork. I discuss how algorithms and AI software should be thought of as tools for creating art and design, and can do so in many different ways.

Aaron Hertzmann is a Principal Scientist at Adobe Research. He received a BA in computer science and art & art history from Rice University in 1996, and a PhD in computer science from New York University in 2001. He was a Professor at University of Toronto for 10 years, and has also worked at Pixar Animation Studios, University of Washington, Microsoft Research, Mitsubishi Electric Research Lab, and Interval Research Corporation. He is an Affiliate Professor at University of Washington, an ACM Fellow, an IEEE Fellow, and the Editor-in-Chief of Foundations and Trends in Computer Graphics and Vision.

- Elizabeth F. Churchill

Amplifying Design Creativity with AI.

In this talk, Elizabeth will reflect on areas where AI can help with design creativity and design practice, focusing particularly on interaction design. She will offer a framework and offer some examples from the work in her teams and from the design world more generally.

Currently a Director of User Experience at Google, Dr. Elizabeth Churchill is an applied social scientist working in the area of human computer interaction (HCI). and user experience (UX). Her current focus is on effective designer and developer tooling. Prior to taking up her current position at Google, Elizabeth has built and managed HCI research teams in a number of well-known companies, including eBay, Yahoo!, PARC and FXPAL – Fuji Xerox’s Research lab. Elizabeth has more than 50 patents granted or pending, seven academic books, and over 100 publications in theoretical and applied psychology, cognitive science, human-computer interaction, mobile and ubiquitous computing, and computer mediated communication and social media. In 2016, she received the Citris-Banatao Institute Athena Award for Executive Leadership. She received her PhD in Cognitive Science from the University of Cambridge, and both her BSc. and MSc. (in Experimental Psychology and in Knowledge Based Systems respectively) from the University of Sussex in the UK. She holds honorary doctorates from the University of Sussex (UK) and Stockholm University. Elizabeth is a Fellow and a Distinguished Speaker of the Association for Computing Machinery (ACM) and a member of the ACM’s CHI Academy. She served as Executive Vice President of the ACM from 2018-2020.

Presentation slides:
Amplifying Design Creativity with AI

- Gerard de Melo

Appearances Matter: Enhancing the Presentation of Text using Cross-Modal Representation Learning and Emotion Analysis.

The way a text is presented can substantially affect how it is perceived, as shown in a range of different psychological studies. This talk presents a series of approaches to enhance the presentation of a text by identifying the most suitable fonts, color palettes, images, and emojis that can be applied. This is achieved using algorithms that induce cross-modal vector representations in order to bridge different modalities, in part drawing on emotion analysis to predict associations with particular affective states such as surprise or optimism. With this, we can ultimately enhance the appearance of a text either based on its textual content, or also in response to specific queries issued by a designer, e.g., “fonts like this one but happier and more modern”. The talk concludes with a diverse set of examples and use cases of such approaches.

Gerard de Melo is a professor at the Hasso Plattner Institute for Digital Engineering and the University of Potsdam, Germany, where he holds the Chair for Artificial Intelligence and Intelligent Systems. He has published over 150 papers, with Best Paper awards at CIKM 2010, ICGL 2008, and the NAACL 2015 Workshop on Vector Space Modeling, as well as an ACL 2014 Best Paper Honorable Mention, a Best Student Paper Award nomination at ESWC 2015, and the WWW 2011 Best Demonstration Award, among others. Previously, he was a professor at Rutgers University in New Jersey and at Tsinghua University in Beijing, and a Post-Doctoral Research Scholar at ICSI/UC Berkeley. He received his doctoral degree at the Max Planck Institute for Informatics.

Presentation slides:
Appearances Matter: Enhancing the Presentation of Text using Cross-Modal Representation Learning and Emotion Analysis

Further details are available at

PC Members

  • Paolo Rosso
  • Esaú Villatoro
  • Rajiv Jain
  • Vlad Morariu
  • Sungchul Kim
  • Handong Zhao
  • Lidan Wang
  • Vishwa Vinay
  • Matt Fisher
  • Nanxuan Zhao
  • Rynson W.H. Lau
  • Carlos Bobed
  • Gerard de Melo
  • Zhouhui Lian
  • Nam Wook Kim
  • Ying Cao
  • Debanjan Mahata
  • Rakesh Gosangi
  • Gaku Morio

Workshop Co-Chairs