An unsupervised method for word sense disambiguation using a bilingual comparable corpus was developed. First, it extracts statistically significant pairs of related words from th...
The method based on local features has an advantage that the important local motion feature is represented as bag-of-features, but lacks the location information. Additionally, in ...
Novelty detection involves identifying novel patterns. They are not usually available during training. Even if they are, the data quantity imbalance leads to a low classification ...
Our goal is for robots to learn conceptual systems su cient for natural language and planning. The learning should be autonomous, without supervision. The rst steps in building a ...