Learning patterns of human behavior from sensor data is extremely important for high-level activity inference. We show how to extract a person’s activities and significant plac...
Text representation is a central task for any approach to automatic learning from texts. It requires a format which allows to interrelate texts even if they do not share content w...
Abstract: Cascade process, such as wastewater treatment plant, includes many nonlinear subsystems and many variables. When the number of sub-systems is big, the input-output relati...
Scoring sentences in documents given abstract summaries created by humans is important in extractive multi-document summarization. In this paper, we formulate extractive summariza...
While ITG has many desirable properties for word alignment, it still suffers from the limitation of one-to-one matching. While existing approaches relax this limitation using phra...