This paper describes the design of speech act tags for spoken dialogue corpora and its evaluation. Compared with the tags used for conventional corpus annotation, the proposed speech intention tag is specialized enough to determine system operations. However, detailed information description increases tag types. This causes an ambiguous tag selection. Therefore, we have designed an organization...

This paper investigates model merging, a technique for deriving Markov models from text or speech corpora. Models are derived by starting with a large and specific model and by successively combining states to build smaller and more general models. We present methods to reduce the time complexity of the algorithm and report on experiments on deriving language models for a speech recognition tas...

A b stract The Xerox Part-of-Speech Tagger (XPOST) claims to be practical. One aspect of practicality as defined here is reusability. Thus it is meant to be easy to port XPOST to a new language. To test this, XPOST was ported to Swedish. This port is described and evaluated. In previous work on part-of-speech tagging, a practical part-of-speech tagger was defined as one with the following set o...

the objective of this experiment was comparison blood serotonin levels in ascetic and non ascitic broilers of three strains (ross, arbor acres plus and cobb). to this purpose, a factorial test in crd was applied. in each of these three strains, 12 ascitic and 12 non ascitic broilers were selected. after tagging and blood sampling, all of blood samples were divided in two parts. one part was app...

Parsing speech requires a richer representation than 1-best or n-best hypotheses, e.g. lattices. Moreover, previous work shows that part-of-speech (POS) tags are a valuable resource for parsing. In this paper, we therefore explore a joint modeling approach of automatic speech recognition (ASR) and POS tagging to enrich ASR word lattices. To that end, we manipulate the ASR process from the prono...

We propose a cascaded linear model for joint Chinese word segmentation and partof-speech tagging. With a character-based perceptron as the core, combined with realvalued features such as language models, the cascaded model is able to efficiently utilize knowledge sources that are inconvenient to incorporate into the perceptron directly. Experiments show that the cascaded model achieves improved...