Answers are grounded in this paper and cite their sources.
This paper describes our current experiments in snippet generation and tweet contextualization. These experiments are based on work reported in 2011 [2] and 2012 [1] and represent refinements of those earlier techniques. Four of our snippet generation runs produced top-ranked results in the INEX 2012 competition; these serve as the basis for our 2013 experiments in snippet generation. Our 2013 tweet contextualization run produced a top-ranked result as well. The methodologies employed and the results obtained are described below. 1
No takes yet. Share an insight, caveat, or question.
Crouch et al. (2013) studied this question.
Synapse has enriched 5 related papers. Consider them for comparative context: