Paper: Improving the Recognizability of Syntactic Relations Using Contextualized Examples

ACL ID P14-2045
Title Improving the Recognizability of Syntactic Relations Using Contextualized Examples
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2014
Authors

A common task in qualitative data analy- sis is to characterize the usage of a linguis- tic entity by issuing queries over syntac- tic relations between words. Previous in- terfaces for searching over syntactic struc- tures require programming-style queries. User interface research suggests that it is easier to recognize a pattern than to com- pose it from scratch; therefore, interfaces for non-experts should show previews of syntactic relations. What these previews should look like is an open question that we explored with a 400-participant Me- chanical Turk experiment. We found that syntactic relations are recognized with 34% higher accuracy when contextual ex- amples are shown than a baseline of nam- ing the relations alone. This suggests that user interfaces should display contex- tual...