目录 Introduction Chapter 1.Linguistic Resources for NLP 1.1.The concept of a corpus 1.2.Corpus taxonomy 1.2.1.Written versus spoken 1.2.2.The historical point of view 1.2.3.The language of corpora 1.2.4.Thematic representativity 1.2.5.Age range of speakers 1.3.Who collects and distributes corpora 1.3.1.The Gutenberg project 1.3.2.The Linguistic Data Consortium 1.3.3.European Language Resource Agency 1.3.4.Open Language Archives Community 1.3.5.Miscellaneous 1.4.The lifecycle of a corpus 1.4.1.Needs analysis 1.4.2.Design of scenarios to collect data for the corpus 1.4.3.Collection of the corpus 1.4.4.Transcription 1.4.5.Corpus annotation 1.4.6.Corpus documentation 1.4.7.Statistical analysis of data 1.4.8.The use of corpora in NLP 1.5.Examples of existing corpora 1.5.1.American National Corpus 1.5.2.Oxford English Corpus 1.5.3.The Grenoble Tourism Office Corpus Chapter 2.The Sphere of Speech 2.1.Linguistic studies of speech 2.1.1.Phonetics 2.1.2.Phonology 2.2.Speech processing 2.2.1.Automatic speech recognition 2.2.2.Speech synthesis Chapter 3.Morphology Sphere 3.1.Elements of morphology 3.1.1.Morphological typology 3.1.2.Morphology of English 3.1.3.Parts of speech 3.1.4.Terms, collocations and colligations 3.2.Automatic morphological analysis 3.2.1.Stemming 3.2.2.Regular expressions for morphological analysis 3.2.3.Informal introduction to finite-state machines 3.2.4.Two-level morphology and FST 3.2.5.Part-of-speech tagging Chapter 4.Syntax Sphere 4.1.Basic syntactic concepts 4.1.1.Delimitation of the field of syntax
以下为对购买帮助不大的评价