Traditionally, machine learning approaches for information extraction require human annotated data that can be costly and time-consuming to produce. However, in many cases, there ...
We present three systems for surface natural language generation that are trainable from annotated corpora. The first two systems, called NLG1 and NLG2, require a corpus marked on...
Background: Proteins are comprised of one or several building blocks, known as domains. Such domains can be classified into families according to their evolutionary origin. Wherea...
Elon Portugaly, Amir Harel, Nathan Linial, Michal ...
We are developing a testbed for learning by demonstration combining spoken language and sensor data in a natural real-world environment. Microsoft Kinect RGBDepth cameras allow us...
Given a query image of an object, our objective is to retrieve all instances of that object in a large (1M+) image database. We adopt the bag-of-visual-words architecture which ha...
Ondrej Chum, James Philbin, Josef Sivic, Michael I...