Creating labeled training data for relation extraction is expensive. In this paper, we study relation extraction in a special weakly-supervised setting when we have only a few see...
Personalized search systems have evolved to utilize heterogeneous features including document hyperlinks, category labels in various taxonomies and social tags in addition to free...
In order to support the navigation in huge document collections efficiently, tagged hierarchical structures can be used. Often, multiple tags are used to describe resources. For u...
Relation extraction, the process of converting natural language text into structured knowledge, is increasingly important. Most successful techniques use supervised machine learni...
This paper presents an efficient approach for copies detection in a large videos archive consisting of several hundred of hours. The video content indexing method consists of ext...