Adverse drug events and drug-drug interactions are a major concern in patient care. Although databases exist to provide information about drugs, they are not always up-to-date and complete (particularly regarding pharmacogenetics). We propose a methodology based on automatic summarization to identify drug information in Medline citations and present results to the user in a convenient form. We ...

Distributed systems are often difficult to debug and understand. A typical way of gaining insight into system behavior is by inspecting execution logs. However, manual inspection of logs is an arduous process. To support this task we developed Synoptic. Synoptic outputs a concise graph representation of logged events that captures temporal invariants mined from the log. We applied Synoptic to s...

Digitization of lengthy personal experiences would be made possible by constant recording using wearable video cameras. It is conceivable that the resulting amount of video content would be extraordinarily large. In order to retrieve and browse the desired scenes, a vast amount of video would need to be organized with structural information. In this paper, we attempt to develop a “Wearable Imag...

We describe the beginning stages of our work on summarizing chat, which is motivated by our observations concerning the information overload of US Navy watchstanders. We describe the challenges of summarizing chat and focus on two chat-specific types of summarizations we are interested in: thread summaries and temporal summaries. We then discuss our plans for addressing these challenges and eva...

This project is aimed to develop the system for summarizing and translating the agricultural information from English to Thai by using statistical and frame based approach. The system consists of 4 modules: Gathering Module, Indexing and Clustering Module, Summarizing Module and Translation Module. At the current state, we consider only the translation of agricultural summary articles, which ha...

Many applications generate massive data streams. Summarizing such massive data requires fast, small space algorithms to support post-hoc queries and mining. An important observation is that such streams are rarely uniform, and real data sources typically exhibit significant skewness. These are well modeled by Zipf distributions, which are characterized by a parameter, z, that captures the amoun...

With vast amounts of text being available in electronic format, such as news and social media, automatic multi-document summarization can help extract the most important information. We present and evaluate a novel method for automatic extractive multi-document summarization. The method is purely combinatorial, based on bicliques in the bipartite word-sentence occurrence graph. It is particular...

In recent years, Online Social Media (OSM) has established itself as one of the most significant sources of situational information during any natural or man-made disaster. Real-time summarization of this rapidly posted huge volume of crowdsourced responses is a common requirement for emergency relief and preparedness when time is critical. Our semi-automatic method exploits a combination of Su...

Large-scale, highly-interconnected networks pervade our society and the natural world around us, including the World Wide Web, social networks, knowledge graphs, genome and scientific databases, medical and government records. The massive scale of graph data often surpasses the available computation and storage resources. Besides, users get overwhelmed by the daunting task of understanding and ...

How can one find a subset, ideally as small as possible, that well represents a massive dataset? I.e., its corresponding utility, measured according to a suitable utility function, should be comparable to that of the whole dataset. In this paper, we formalize this challenge as a submodular cover problem. Here, the utility is assumed to exhibit submodularity, a natural diminishing returns condit...