DeScipher: A Text Simplification Tool for Science Journalism
Yea Seul Kim, Jessica Hullman and Eytan Adar
Complex jargon often makes scientific work less accessible to the general public. By employing a set of specific reporting strategies, journalists bridge these groups by delivering information about scientific advances in a readable, engaging way. One such strategy is using simpler terms in place of complex jargon. To assist in this process, we introduce DeScipher, a text editor application that suggests and ranks possible simplifications of complex terminology to a journalist while she is authoring an article. DeScipher applies simplification rules derived from a large collection of scientific abstracts and associated author summaries, and accounts for textual context in making suggestions to the journalist. In evaluating our system, we show that DeScipher is a viable application for producing useful simplifications of scientific and other terms by comparing to prior techniques used on other corpora. We also propose concrete opportunities for future development of "journalist-in-the-loop" tools for aiding journalists in enacting science reporting strategies.
Pre-print: PDF (310Kb), Computation+Journalism'15, New York, NY, October 2-3, 2015.