Abstract. Existing automated MT evaluation methods often require expert human translations. These are produced for every language pair evaluated and, due to this expense, subsequen...
Active learning (AL) is a framework that attempts to reduce the cost of annotating training material for statistical learning methods. While a lot of papers have been presented on...
We have created a gradient-based face navigation interface that allows users to explore a large face space based on an eigenface technique. This approach to synthesizing faces con...
It is known that convolutional neural networks (CNNs) are efficient for optical character recognition (OCR) and many other visual classification tasks. This paper applies error-co...
Previously topic models such as PLSI (Probabilistic Latent Semantic Indexing) and LDA (Latent Dirichlet Allocation) were developed for modeling the contents of plain texts. Recent...