Question generation is the parallel task of question answering, where given an input context and, optionally, an answer, the goal is to generate a relevant and fluent natural language question. Although recent works on question generation have experienced success by utilizing sequence-to-sequence models, there is a need for question generation models to handle increasingly complex input contexts to produce increasingly detailed questions. Multi-hop question generation is a more challenging task that aims to generate questions by connecting multiple facts from multiple input contexts. In this work, we apply a transformer model to the task of multi-hop question generation without utilizing any sentence-level supporting fact information. We utilize concepts that have proven effective in single-hop question generation, including a copy mechanism and placeholder tokens. We evaluate our model’s performance on the HotpotQA dataset using automated evaluation metrics, including BLEU, ROUGE and METEOR and show an improvement over the previous work.

We investigate the impact of using anthropomorphized data graphics over standard charts on viewers' empathy for, and prosocial behavior toward suffering populations, in the context of human rights narratives. We present a series of experiments conducted on Amazon Mechanical Turk, in which we compare various forms of anthropomorphized data graphics-ranging from a single human figure that "fills up" to show proportional data, to separated groups of individual human beings-with a standard chart baseline. Each experiment uses two carefully crafted human rights data-driven stories to present the graphics. Contrary to our expectations, we consistently find that anthropomorphized data graphics and standard charts have very similar effects on empathy and prosocial behavior.