Shiyan Yan

Cristina Garbacea, Samuel Carton, Shiyan Yan et al.

We conduct a large-scale, systematic study to evaluate the existing evaluation methods for natural language generation in the context of generating online product reviews. We compare human-based evaluators with a variety of automated evaluation procedures, including discriminative evaluators that measure how well machine-generated text can be distinguished from human-written text, as well as word overlap metrics that assess how similar the generated text compares to human-written references. We determine to what extent these different evaluators agree on the ranking of a dozen of state-of-the-art generators for online product reviews. We find that human evaluators do not correlate well with discriminative evaluators, leaving a bigger question of whether adversarial accuracy is the correct objective for natural language generation. In general, distinguishing machine-generated text is challenging even for human evaluators, and human decisions correlate better with lexical overlaps. We find lexical diversity an intriguing metric that is indicative of the assessments of different evaluators. A post-experiment survey of participants provides insights into how to evaluate and improve the quality of natural language generation systems.

Sang Won Lee, Yi Wei Yang, Shiyan Yan et al.

In the early stages of designing graphical user interfaces (GUIs), the look (appearance) can be easily presented by sketching, but the feel (interactive behaviors) cannot, and often requires an accompanying description of how it works (Myers et al. 2008). We propose to use crowdsourcing to augment early sketches with interactive behaviors generated, used, and reused by collective "wizards-of-oz" as opposed to a single wizard as in prior work (Davis et al. 2007). This demo presents an extension of Apparition (Lasecki et al. 2015), a crowd-powered prototyping tool that allows end users to create functional GUIs using speech and sketch. In Apparition, crowd workers collaborate in real-time on a shared canvas to refine the user-requested sketch interactively, and with the assistance of the end users. Our demo extends this functionality to let crowd workers "demonstrate" the canvas changes that are needed for a behavior and refine their demonstrations to improve the fidelity of interactive behaviors. The system then lets workers "remix" these behaviors to make creating future behaviors more efficient.