Many studies have focused on the facts that numeral classifiers give decisive clues to the semantic categorizing of nouns. However, few studies have analyzed the ontological relationships of classifiers or the construction of classifier ontology. In this paper, a semi-automatic method of extracting and representing the various ontological relations of Korean numeral classifiers is proposed. Sha...

In this paper we discuss a method for semi-supervised training of CNNs. By using auto-encoders to extract features from unlabeled images, we can train CNNs to accurately classify images with only a small set of labeled images. We show our method’s results on a shallow CNN using the CIFAR-10 dataset, and some preliminary results on a VGG-16 network using the STL-10 dataset.

We describe an effort to annotate a corpus of natural language instructions consisting of 662 wet lab protocols to facilitate automatic or semi-automatic conversion of protocols into a machine-readable format and benefit biological research. Experimental results demonstrate the utility of our corpus for developing machine learning approaches to shallow semantic parsing of instructional texts. W...

plant biomass is an important factor for determining arid and semi-aridrangelands capacity. due to the lack of proper and annual sampling of rangelands, there areno suitable data to determine biomass, range condition and proper range managementoperations. plant biomass is one of the measurable attributes that can be assessed inrangeland studies. since the clip and weight method is destructive a...

Termination is one of the central properties of term rewriting systems (TRSs for short). A TRS is called terminating if it does not admit any infinite rewrite sequence. The efforts to find classes of TRSs whose termination is decidable have been made for decades and several positive results have been proposed, for example, right-ground TRSs and right-linear shallow TRSs. In this research, we st...

This paper describes the text-to-speech synthesis system developed for the Blizzard Challenge 2016 by members of the ADAPT centre and colleagues from associated projects. The task was to build a synthetic voice for reading audiobooks to children, from a speech database of audiobooks around 5 hours long. Our entry system is an HMM-based parametric speech synthesizer which was built using a subse...