Despite the recent advances in text classification and the performance improvement yielded by Transformers models, the absence or inaccessibility of an adequate dataset to train a text classifier motivates the choice for alternative routes. In ...

Temporal information extracted from texts and normalized to some standard format has been exploited in a variety of tasks such as information retrieval and question answering. Classifying documents into categories using temporal features has not yet ...

Representation of news events as latent feature vectors is essential for several tasks, such as news recommendation, news event linking, etc. However, representations proposed in the past fail to capture the complex network structure of news events. In ...

News classification is among essential needs for people to organize, better understand, and utilize information from the Internet. This motivates the authors to propose a novel method to classify news from social media. First, we propose to vectorize an ...

We present initial results of our effort to build an extensive and complete taxonomy of events described in news articles. By crawling Wikipedia's current events portal we identified nine top-level event types. Using articles referenced by the portal we ...

Personalisation tasks require the use of semantic information, extracted from multimedia streams, in order to achieve the benefits of automatic matching user preferences with multimedia content meaning. Text-based classification techniques may be used ...

With the development of content-based multimedia services, the personalization task has become increasingly important. There is a need for semantic information knowledge, extracted from multimedia streams, in order to achieve the benefits of automatic ...

In this project summary, we briefly present the disease monitoring and situational awareness infrastructure developed in BioPortal, our NSF-funded Infectious Disease Informatics project. We focus on two areas: social network analysis for Severe Acute ...

There are three common challenges in real-world classification applications, i.e. how to use domain knowledge, how to resist noisy samples and how to use unlabeled data. To address these problems, a novel classification framework called Mutually ...