The New Yorker publishes a weekly captionless cartoon. More than 5,000 readers submit captions for it. The editors select three of them and ask the readers to pick the funniest one. We describe an experiment that compares a dozen automatic methods for selecting the funniest caption. We show that negative sentiment, human-centeredness, and lexical centrality most strongly match the funniest captions, followed by positive sentiment. These results are useful for understanding humor and also in the design of more engaging conversational agents in text and multimodal (vision+text) systems. As part of this work, a large set of cartoons and captions is being made available to the community.

We investigate the task of generating coherent survey articles for scientific topics. We introduce an extractive summarization algorithm that combines a content model with a discourse model to generate coherent and readable summaries of scientific topics using text from scientific articles relevant to the topic. Human evaluation on 15 topics in computational linguistics shows that our system produces significantly more coherent summaries than previous systems. Specifically, our system improves the ratings for coherence by 36% in human evaluation compared to C-Lexrank, a state of the art system for scientific article summarization.