In this paper, we present an efficient general-purpose objective no-reference (NR) image quality assessment (IQA) framework based on unsupervised feature learning. The goal is to...
We describe an approach for acquiring the domain-specific dialog knowledge required to configure a task-oriented dialog system that uses human-human interaction data. The key aspe...
Alert correlation systems are post-processing modules that enable intrusion analysts to find important alerts and filter false positives efficiently from the output of Intrusion...
This paper presents an unsupervised learning approach to building a non-English (Arabic) stemmer. The stemming model is based on statistical machine translation and it uses an Eng...
The AutoFeed system automatically extracts data from semistructured web sites. Previously, researchers have developed two types of supervised learning approaches for extracting we...