Stanford dependencies are widely used in natural language processing as a semanticallyoriented representation, commonly generated either by (i) converting the output of a constitu...
We propose a latent variable model to enhance historical analysis of large corpora. This work extends prior work in topic modelling by incorporating metadata, and the interactions...
William Yang Wang, Elijah Mayfield, Suresh Naidu, ...
Extracting sentiment and topic lexicons is important for opinion mining. Previous works have showed that supervised learning methods are superior for this task. However, the perfo...
Fangtao Li, Sinno Jialin Pan, Ou Jin, Qiang Yang, ...
We address the problem of learning the mapping between words and their possible pronunciations in terms of sub-word units. Most previous approaches have involved generative modeli...
Abstract. In this paper we present the architecture of an Adaptive Educational Hypermedia System, named INSPIRE. This particular system, throughout its interaction with the learner...
Kyparisia A. Papanikolaou, Maria Grigoriadou, Harr...