Learn More
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) dataset (106 tokens) combined with a relatively modest (in the order of 108(More)
The present paper examines three methods of intonational stylization in the Czech language: a sequence of pitch accents, a sequence of boundary tones, and a sequence of contours. The efficiency of these methods was compared by means of a neural network which predicted the f0 curve from each of the three types of input, with subsequent perceptual assessment.(More)
ii Introduction We are pleased to present the papers accepted for presentation at the an established tradition at the annual meetings of ACL, offers students the opportunity to present their work in a setting embedded in the main conference and features ACL's efforts to invest in young researchers who will be a part of the research community in(More)
  • 1