We address appropriate user modeling in order to generate cooperative responses to each user in spoken dialogue systems. Unlike previous studies that focus on user’s knowledge o...
We train a decision tree inducer (CART) and a memory-based classifier (MBL) on predicting prosodic pitch accents and breaks in Dutch text, on the basis of shallow, easy-to-comput...
Erwin Marsi, Martin Reynaert, Antal van den Bosch,...
Named entity (NE) recognition is a task in which proper nouns and numerical information in a document are detected and classified into categories such as person, organization, loc...
This paper presents an unsupervised learning approach to building a non-English (Arabic) stemmer. The stemming model is based on statistical machine translation and it uses an Eng...
Standard IR systems can process queries such as “web NOT internet”, enabling users who are interested in arachnids to avoid documents about computing. The documents retrieved ...