The University of Amsterdam (ILPS.UvA) at TREC 2015 Temporal Summarization Track

In this paper we report on our participation in the TREC 2015 Temporal Summarization track, aimed at encouraging the development of systems able to detect, emit, track, and summarize sentence length updates about a developing event. We address the task by probing the utility of a variety of information retrieval based methods in capturing useful, timely and novel updates during unexpected news events such as natural disasters or mass protests, when high volumes of information rapidly emerge. We investigate the extent to which these updates are retrievable, and explore ways to increase the coverage of the summary by taking into account the structure of documents. We find that our runs achieve high scores in terms of comprehensiveness, successfully capturing the relevant pieces of information that characterize an event. In terms of latency, our runs perform better than average. We present the specifics of our framework and discuss the results we obtained.