We describe a method for prediction of linguistic structure in a language for which only unlabeled data is available, using annotated data from a set of one or more helper languages. Our approach is based on a model that locally mixes between supervised models from the helper languages. Parallel data is not used, allowing the technique to be applied even in domains where human-translated texts ...

This paper presents an algorithm for tagging words whose part-of-speech properties are unknown. Unlike previous work, the algorithm categorizes word tokens in con$ezt instead of word ~ypes. The algorithm is evaluated on the Brown Corpus.

Many corpus linguists make the tacit assumption that part-of-speech frequencies remain constant during the period of observation. In this article, we will consider two related issues: (1) the reliability of part-of-speech tagging in a diachronic corpus, and (2) shifts in tag ratios over time. The purpose is both to serve the users of the corpus by making them aware of potential problems, and to...

Sentence types typical to Swedish clinical text were extracted by comparing sentence part-of-speech tag sequences in clinical and in standard Swedish text. Parsings by a syntactic dependency parser, trained on standard Swedish, were manually analysed for the 33 sentence types most typical to clinical text. This analysis resulted in the identification of eight error types, and for two of these e...

The paper reports the approach of cyut system in NTCIR-8 MOAT subtask. We submitted the results of opinion judgment and polarity judgment in Traditional Chinese. Our study focused on automatically generated templates as the only features of classifier. The templates combining words with Part-of-speech or named-entity (POS/NE) tags are acquired from the training set. Experiment results show that...

This paper describes a systematic investigation of the extent to which the part of speech of words can be identified from their prefixes and suffixes. The results indicate that it is possible to determine, with 95 per cent accuracy, the inclusive part of speech of an affixed word from a consideration of its prefixes, suffixes, and length. By "inclusive" parts of speech we mean a string that wil...

Treating shallow parsing as part-of-speech tagging yields results comparable with other, more elaborate approaches. Using the CoNLL 2000 training and testing material, our best model had an accuracy of 94.88%, with an overall FB1 score of 91.94%. The individual FB1 scores for NPs were 92.19%, VPs 92.70% and PPs 96.69%.

This is a pilot study which aims at the design of a Chinese morphological analyzer which is in state to predict the syntactic and semantic properties of nominal, verbal and adjectival compounds. Morphological structures of compound words contain the essential information of knowing their syntactic and semantic characteristics. In particular, morphological analysis is a primary step for predicti...

The use of distance functions in order to determine nearest instance class at Memory Based Learning methods may be crucial when there are no exact matchings. We add relative information over unknown feature values to improve the information extract on the training instances. An experiment was carried out for Spanish Part-Of-Speech tagging of unknown words nding a better performance with our mod...

We investigate the problem of unsupervised part-of-speech tagging when raw parallel data is available in a large number of languages. Patterns of ambiguity vary greatly across languages and therefore even unannotated multilingual data can serve as a learning signal. We propose a non-parametric Bayesian model that connects related tagging decisions across languages through the use of multilingua...