Silent Day Detection in Real-Time Summarization Track

Kuang Lu, Peilin Yang, Hui Fang
2017 Text Retrieval Conference  
In microblog retrieval, a system's ability to detect silent days and "shut up" during these days have an huge impact on its performance [1] . Therefore, in this year's Real-Time Summarization Track, we focus on detecting silent days. More specifically, we propose two silent day detectors phrase-based weighted information gain and local query term coherence, both of which focus on using query terms collectively instead of individually. Track results suggest that our methods can effectively
more » ... silent days, which subsequently results in promising performances for both scenarios.
dblp:conf/trec/LuY017 fatcat:z3a77wodyfecxd3vrjwfu4lxom