Many real-world sequence learning tasks require the prediction of sequences of labels from noisy, unsegmented input data. In speech recognition, for example, an acoustic signal is...
In this paper we present a method to cluster large datasets that change over time using incremental learning techniques. The approach is based on the dynamic representation of clus...
We are studying long term sequence prediction (forecasting). We approach this by investigating criteria for choosing a compact useful state representation. The state is supposed t...
Using abundant Web resources to mine Chinese term translations can be applied in many fields such as reading/writing assistant, machine translation and crosslanguage information r...
Individuals often use search engines to return to web pages they have previously visited. This behaviour, called refinding, accounts for about 38% of all queries. While researcher...