This book addresses the problem of creating linguistic taggers for resource-poor languages using existing taggers in resource rich languages. Linguistic taggers are classifiers that map individual words or phrases from a sentence to a set of tags. Linguistic taggers are usually trained using supervised learning algorithms.The proposed approach does not require that the input sentence be translated into the source language. Instead, projection of linguistic tags is accomplished through the use of a parallel corpus, which is a collection of texts that are available in a source language and a target language. The correspondence between words of the source and target language allows to project tags from source to target language words.A parallel corpus of the source and target languages might not be readily available for many language pairs. To deal with this problem, we describe a system for automatic acquisition of aligned, bilingual corpora from pre-specified domains on the World Wide...

Под заказ:
	OZON.ru - 2785 руб.	Перейти

Рейтинг книги: 4 из 5, 3 голос(-ов).