This paper investigates the use of colour and texture cues for segmentation of images within two specified domains. The first is the Sowerby dataset, which contains one hundred co...
We present a method of grounded word learning that is powerful enough to learn the meanings of first and second person pronouns. The model uses the understood words in an utteran...
In this paper we introduce a modular, highly flexible, opensource environment for data generation. Using an existing graphical data flow tool, the user can combine various types...
The transfer of tacit knowledge is important in ensuring that an organisations most valuable assets do not walk out the door. While much controversy surrounds the definition of ta...
We describe an open-source toolkit for statistical machine translation whose novel contributions are (a) support for linguistically motivated factors, (b) confusion network decodi...
Philipp Koehn, Hieu Hoang, Alexandra Birch, Chris ...