A resource-light approach to morpho-syntactic tagging. * Anna Feldman and Jirka Hana.
Lieve Macken · Literary and Linguistic Computing · 2010
This volume deals with the problem of morpho-syntactic tagging, i.e. ‘the process of assigning part-of-speech, case, number, gender, and other morphological information to each word in a corpus’ (p. 2). In its simplest form, a part-of-speech tagger identifies the traditional grammatical categories such as verb, noun, adverb, adjective, preposition, and so on. In the case of morphologically rich languages, the problems of part-of-speech tagging and morphological analysis are closely tied, and both tasks are often integrated into one program. In the domain of natural language processing (NLP), part-of-speech tagging is regarded as a first level of abstraction in text analysis and is often used as a pre-processing module in many language technology applications such as parsing, information retrieval, spelling error correction, speech synthesis, and text mining (Daelemans and van den Bosch 2005, pp. 86–87). Morpho-syntactic taggers thus form an indispensible resource for the development of a wide range of NLP applications.