Abstract. Traditionally, machine learning algorithms such as decision tree learners have employed attribute-value representations. From the early 80's on people have started t...
Recently, language resources (LRs) are becoming indispensable for linguistic research. Unfortunately, it is not easy to find their usages by searching the web even though they mus...
We analyze subword-based language models (LMs) in large-vocabulary continuous speech recognition across four “morphologically rich” languages: Finnish, Estonian, Turkish, and ...
Individuals are interested in the semantic and not necessarily in the presentation of services. The service interaction has to support the quality of the human senses, and since q...
While participating in the HARD track our first question was, what an IR-application should look like that takes into account preference meta-data from the user, without the need ...