ABSTRACT

This part introduction presents an overview of the key concepts discussed in the subsequent chapters. The part provides an extension of Chinese Knowledge Information Processing group's (CKIP) Parts of Speech (POS) Analysis of Contemporary Chinese originally published in 1986. The entries in the CKIP lexicon include not only words, but also sub-lexical units smaller than words, as well as phrases and idioms. In addition to words, there exist 12 'sentences' in the CKIP Lexicon. There are eight major POS classes in the CKIP Lexicon—verbs, non-predicative adjectives, nouns, adverbs, prepositions, connectives, particles, and interjections. Other than non-predicative adjectives and interjections, all the POS classes are further divided into sub-classes based on their semantic and syntactic behaviors. The information of nouns carrying temporal features will be submitted to the parser so as to identify the role of modification without needing to assign multiple POS tags.