pages, including appendixand bibliograp& $51 hardcover T he World of Culinary Superuiswn,

Abstract: A study on classification capability of neural networks is presented, considering two types of architectures with supervised training, namely Multilayer Perceptron (MLP) and Radial-Basis Function (RBF). To illustrate the classifiers’ construction, we have chosen a problem that occurs

We present a method for training a semantic parser using only a knowledge base and an unlabeled text corpus, without any individually annotated sentences. Our key observation is that multiple forms of weak supervision can be combined to train an accurate semantic parser: semantic supervision from a

This paper presents an unsupervised learning algorithm for sense disambiguation that, when trained on unannotated English text, rivals the performance of supervised techniques that require time-consuming hand annotations. The algorithm is based on two powerful constraints -- that words tend to have

will learn robustly and will be reasonably efficient. The main questions in laying out the architecture and then training the MLP are listed below. 1. How many layers of neurodes should we use? 2. How many input nodes should we use? 137 3. How many neurodes in the hidden layers should we use? 4. How

error). Two widely used statistical tests are shown to have high probability of type I error in certain situations and should never be used: a test for the difference of two proportions and a paired-differences t test based on taking several random train-test splits. A third test, a paired

ufal.mff.cuni.cz This paper describes POS tagging experiments with semi-supervised training as an extension to the (supervised) averaged perceptron algorithm, first introduced for this task by (Collins, 2002). Experiments with an iterative training on standard-sized supervised (manually annotated

This paper investigates improving lightly supervised acous-tic model training for an archive of broadcast data. Standard lightly supervised training uses automatically derived decoding hypotheses using a biased language model. However, as the actual speech can deviate significantly from

of Tamil, when significantly more test data than training data is available, we integrated semi-supervised training and speaker adaptation on the test data, and achieved significant additional improvements in STT and KWS. Index Terms — spoken term detection, automatic speech recog-nition, low-resource LTs

I describe the TreeBanker, a graphical tool for the supervised training involved in domain customization of the disambiguation component of a speech- or languageunderstanding system. The TreeBanker presents a user, who need not be a system expert, with a range of properties that distinguish