Artificial Intelligence 人工智能.ppt
Chapter 10Natural Language Processing,Xiu-jun GONG (Ph. D)School of Computer Science and Technology, Tianjin Universitygongxjtju.edu.cn http:/cs.tju.edu.cn/faculties/gongxj/course/ai/,Turing's test,Is a machine is intelligent or not?,If a machine could carry on a conversation (over a teletype) that was indistinguishable from a conversation with a human being, then the machine could be called "intelligent.",Understand the language is the essential step for conservation,Language,We can define a language formally as:a set of symbols (“alphabet”)a set of rules to combine those symbolsThis mathematical definition covers many classes of languages, not just human language.,Java: An artificial (formal) language,fixed set of basic symbols:public, static, for, while, , fixed syntax for symbol combinationpublic static void main (String args) for(int i = 0; i < args.length; i+) ,Natural language,Often much more complicated than an artificial language.Some people view NL as a special kind of formal language as well.It does conform to the formal definition:there are symbolsthere are modes of combinationHowever, there are many levels at which these symbols and rules are defined.,Levels of analysis in Natural language (1),Acoustic properties (phonetics:语音学)defines a basic set of sounds in terms of their featuresstudies the combination of these phonemesHigher-order acoustic features (phonology:语音体系)how combinations of phonemes combine into larger units, with supra-segmental features such as intonation.,Levels of analysis in Natural language (2),Word formation (morphology:形态学)combines morphemes into wordsCombination into longer units in a structure-dependent way (syntax)“legal” word combinations in a languagerecursive phrasal combinationInterpretation (semantics):of words (lexical semantics) of longer units (sentential/propositional semantics)Interpretation in context (pragmatics:语用论),Natural Language Processing,Studies language at all its levels.phonology, morphology, syntax, semanticsfocuses on processcomputational methods to understand and generate human languageOften, NLP is called computational linguistics,Task,Language ModelingMachine TranslationInformation Extraction/RetrievalNamed entity recognitionAutomatic summarizationSpeech recognitionQuestion Answering,Tools for NLP,OpenNLPhttp:/opennlp.sourceforge.net/Stanford NLPhttp:/nlp.stanford.edu/links/statnlp.htmlNLP Toolsuitehttp:/www.julielab.de/Resources/Software/NLP_Tools.htmlResource maintained by Kita http:/www-a2k.is.tokushima-u.ac.jp/member/kita/NLP/nlp_tools.html,
