We generalize the task of finding question paraphrases in a question repository to a novel formulation in which known questions are ranked based on their utility to a new, reference question. We manually annotate a dataset of 60 groups of questions with a partial order relation reflecting the relative utility of questions inside each group, and use it to evaluate meaning and structure aware utility functions. Experimental evaluation demonstrates the importance of using structural information in estimating the relative usefulness of questions, holding the promise of increased usability for social QA sites.
Razvan C. Bunescu, Yunfeng Huang