Networked communications inherently depend on the ability of the sender of a message to indicate through some token how the message should be delivered to a particular recipient. The tokens that refer messages to recipients are variously known as routes, addresses, handles, and names, ordered by their relative nearness to network topology vs. human meaning. All four sorts of token refer in some...

In this paper, we describe the details of our methods for the participation in the subtask of the ImageCLEF 2016 Scalable Image Annotation task: Natural Language Caption Generation. The model we used is the combination of a procedure of encoding and a procedure of decoding, which includes a Convolutional neural network(CNN) and a Long Short-Term Memory(LSTM) based Recurrent Neural Network. We f...

Logistics planning in disaster response phase involves dispatching commodities such as medical materials, personnel, food, etc. to affected areas as soon as possible to accelerate the relief operations. Since transportation vehicles in disaster situations can be considered as scarce resources, thus, the efficient usage of them is substantially important. In this study, we provide a dynamic vehi...

News spread in internet media outlets can be seen as a contagious process generating temporal networks representing the influence between published articles. In this article we propose a methodology based on the application of natural language analysis of the articles to reconstruct the spread network. From the reconstructed network, we show that the dynamics of the news spread can be approxima...

Despite the clear inter-dependency between analyzing the interactions in social networks, and analyzing the natural language content of these interactions, these aspects are typically studied independently. In this paper we present a first step towards finding a joint representation, by embedding the two aspects into a single vector space. We show that the new representation can help improve pe...

Given a spatial network, a spatial neighbourhood, a collection of activities, and a number of clusters to identify, the problem of geometric and network based summarization is to advise our users whether to use a network-based summarization or a geometry-based one. Network summarization is an important societal problem and has been used by athorities to curb crime [15, 5, 12] and respond to nat...

Traditional approaches to the problem of extracting data from texts have emphasized hand-crafted linguisti c knowledge . In contrast, BBN's PLUM system (Probabilistic Language Understanding Model) was developed a s part of a DARPA-funded research effort on integrating probabilistic language models with more traditional linguistic techniques . Our research and development goals are • more rapid ...

This paper describes the basic philosophy and implementation of MPLUS (M+), a robust medical text analysis tool that uses a semantic model based on Bayesian Networks (BNs). BNs provide a concise and useful formalism for representing semantic patterns in medical text, and for recognizing and reasoning over those patterns. BNs are noise-tolerant, and facilitate the training of M+.