Sources of training data suitable for language modeling of conversational speech are limited. In this paper, we show how training data can be supplemented with text from the web ď...
tendees. Extended abstracts ranging from three to four pages in length can be submitted on any relevant topic. Papers will be accepted based on the quality of research and potentia...
This study aims to investigate whether structuring an interaction supports students' elaborative argumentation. The study compares the quality of secondary school students...
In EM and related algorithms, E-step computations distribute easily, because data items are independent given parameters. For very large data sets, however, even storing all of th...
We propose a new method for human action recognition from video sequences using latent topic models. Video sequences are represented by a novel “bag-of-words” representation, w...