Automatically Generating Engaging Presentation Slide Decks
Talented public speakers have thousands of hours of practice. One means of improving public speaking skills is practice through improvisation, e.g. presenting an improvised presentation using an unseen slide deck. We present Tedric, a novel system capable of generating coherent slide decks based on a single topic suggestion. It combines semantic word webs with text and image data sources to create an engaging slide deck with an overarching theme. We found that audience members perceived the quality of improvised presentations using these generated slide decks to be on par with presentations using human created slide decks for the Improvised TED Talk performance format. Tedric is thus a valuable new creative tool for improvisers to perform with, and for anyone looking to improve their presentation skills.
KeywordsComputer-aided and computational creativity Generation Computational intelligence for human creativity
Thank you to the reviewers for their time and attention reviewing this work, as well as for the insightful comments. Thanks to Julian Faid and Dr. Piotr Mirowski for advice and support in the creation of the software. Thank you to Lana Cuthbertson, the producer of TEDxRFT, and to the talented individuals at Rapid Fire Theatre for supporting innovative art. Thank you to all the performers who have done improvised TED talks and shared their views and opinions on how to structure and frame, your help in building the design guide was critical. Thanks to Shaun Farrugia for creating and hosting an online demo of Tedric, making it more easily available for performers of any background to use the system. Thank you to volunteers from the Belgian improvisational comedy group Preparee for volunteering for the evaluation.
- 1.Wilbur, P.K.: Stand up, Speak up, or Shut up. Dembner Books, New York (1981)Google Scholar
- 6.Mathewson, K.W.: Improvised ted talks (2018). https://korymathewson.com/improvised-ted-talks/
- 7.Winiger, S.: Ted-RNN – machine generated ted-talks (2015). https://medium.com/@samim/ted-rnn-machine-generated-ted-talks-3dd682b894c0
- 8.Knight, H.: Silicon-based comedy (2010). https://www.ted.com/talks/heather_knight_silicon_based_comedy
- 9.Mathewson, K.W., Mirowski, P.: Improvised theatre alongside artificial intelligences. In: AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (2017)Google Scholar
- 11.Ranjan, A., Gangadhare, A., Shinde, S.V.: A review on learning based automatic PPT generation using machine learning. Int. J. Sci. Res. Comput. Sci. Eng. Inf. Technol. (IJSRCSEIT) 3, 547–552 (2018)Google Scholar
- 12.Sravanthi, M., Chowdary, C.R., Kumar, P.S.: SlidesGen: automatic generation of presentation slides for a technical paper using summarization. In: FLAIRS Conference (2009)Google Scholar
- 14.Binsted, K., Ritchie, G.: An implemented model of punning riddles. CoRR abs/cmp-lg/9406022 (1994)Google Scholar
- 16.Venour, C.: The computational generation of a class of puns. Master’s thesis, Queen’s University, Kingston, Ontario (1999)Google Scholar
- 20.Jaques, N., Engel, J., Ha, D., Bertsch, F., Picard, R., Eck, D.: Learning via social awareness: improving sketch representations with facial feedback. arXiv preprint arXiv:1802.04877 (2018)