Introduction to NLP Tools.ppt

《Introduction to NLP Tools.ppt》由会员分享，可在线阅读，更多相关《Introduction to NLP Tools.ppt（34页珍藏版）》请在麦多课文档分享上搜索。

1、1,Introduction to NLP Tools,09/23/2003,2,Motivation,Machine Translation From English to FrenchWhats needed?,3,Motivation Contd (1),Syntactic parser Part-Of-Speech Tagger Example: NP - adj noun Morphological Analyzer Example: “tools” - “tool”“Who is he?” - “Who is he ?” Semantic Analyzer Word sense d

2、isambiguate (“wash dishes”) Choose the correct translation,4,Motivation Contd (2),Lexicons The information of the word How many senses? Whats the possible translations of the word? Corpus Useful for learning a tool Useful for evaluation,5,Outline,Lexicons Text corpora Morphological tools Part-Of-Spe

3、ech(POS) taggers Syntactic parsers Semantic knowledge bases and semantic parser Speech tools,6,Lexicons,Definition A repository for words Lexicons in LDC(Linguistic Data Consortium) creating and sharing linguistic resources: data, tools and standards. CELEX WordNet,7,CELEX,Dutch Center for Lexical I

4、nformation Lexical databases of English , Dutch and German 21,000 nouns, 8,000 adjectives and 6,000 verbs English: English Orthography, Lemmas English Phonology, Lemmas English Morphology, Lemmas English Syntax, Lemmas English Frequency, Lemmas English Orthography, Wordforms English Phonology, Wordf

5、orms English Morphology, Wordforms English Frequency, Wordforms English Corpus Types English Frequency, Syllables,8,WordNet,A database of lexical relations Inspired by current psycholinguistic theories of human lexical memory Synset: a set of synonyms, representing one underlying lexical concept Exa

6、mple: fool chump, fish, fool, gull, mark, patsy, fall guy, sucker, schlemiel, shlemiel, soft touch, mug Relations link the synsets: hypernym, Has-Member, Member-Of, Antonym, etc.,9,WordNet Contd,Example pu-erh.cs.utexas.edu$ wn bike -partnPart Meronyms of noun bike2 senses of bike Sense 1 motorcycle

7、, bikeHAS PART: mudguard, splashguard Sense 2 bicycle, bike, wheelHAS PART: bicycle seat, saddleHAS PART: bicycle wheelHAS PART: chainHAS PART: coaster brakeHAS PART: handlebarHAS PART: mudguard, splashguardHAS PART: pedal, treadle, foot leverHAS PART: sprocket, sprocket wheel,Example Pu-erh.cs.utex

8、as.edu$wn bikeInformation available for noun bike-hypen Hypernyms-hypon, -treen Hyponyms & Hyponym Tree-synsn Synonyms (ordered by frequency)-partn Has Part Meronyms-meron All Meronyms-famln Familiarity & Polysemy Count-coorn Coordinate Sisters-simsn Synonyms (grouped by similarity of meaning)-hmern

9、 Hierarchical Meronyms-grepn List of Compound Words-over Overview of SensesInformation available for verb bike-hypev Hypernyms-hypov, -treev Hyponyms & Hyponym Tree-synsv Synonyms (ordered by frequency)-famlv Familiarity & Polysemy Count-framv Verb Frames-simsv Synonyms (grouped by similarity of mea

10、ning)-grepv List of Compound Words-over Overview of Senses,10,Corpus,Definition Collections of text and speech LDC Penn Treebank DSO Hansard,11,Some of the Top Corpus from LDC,TIPSTER Information Retrieval, Data Extrraction datasets TIPSTER project, TREC project TIMIT Acoustic-Phonetic Continuous Sp

11、eech Corpus A corpus of read speech designed to Provide speech data for the acquisition of acousticphonetic knowledge Useful for the development and evaluation of automatic speech recognition systems ECI(European Corpus Initiative Multilingual Corpus) multilingual electronic text corpus NTIMIT A pho

12、netically balanced, continuous speech, telephone bandwidth speech database,12,Penn Treebank,A collection of corpora Tagged with POS, Syntactic roles, predicate/argument structure, dysfluency annotation How are they made Hand correction of the output of an errorful automatic process 3 million words 1

13、 million words tagged with predicate/argument structure for extraction semantic knowledge,13,Penn Treebank Cont.d,Corpora Wall Street Journal ATIS (Air Travel Information System) Brown Corpus IBM Manual Sentences Library of America Texts: Mark Twain, Henry Adams, Herman Melville . MUC-3 Messages,Exa

14、mple: ( (S (NP-SBJ Rally s)(VP operatesandfranchises(NP (NP (QP about 160)fast-food restaurants)(PP-LOC throughout(NP the U.S)Seeking/VBG to/TO block/VB the/DT investors/NNS from/IN buying/VBG more/JJR shares/NNS ./.,14,DSO,Word Sense Corpus Contains sentences in which about 192,800 word occurrences

15、 have been tagged with WordNet senses Taken from the Brown corpus and the Wall Street Journal corpus 121 nouns and 70 verbs,15,Hansard,Official records (Hansards) of the 36th Canadian Parliament, both in English of French 1.3 million pairs of aligned sentences of English and French Example Comme il

16、est 14 h 30, la Chambre sajourne jusquxe0 lundi prochain, xe0 11 heures, conformxe9ment au paragraphe 24(1) du Rxe8glement. It being 2.30 p.m., the House stands adjourned until Monday next at 11 a.m., pursuant to Standing Order 24(1). Useful for Machine Translation,16,Morphological Tools,PC-KIMMO A

17、two-level morphological parser Porter Stemmer Penn Treebank Tokenizer Seperate document into words “dog?” - “dog ?”,17,Porter Stemmer,Simple algorithm, use a set of cascaded rewrite rules Example Ational-ATE (relational-relate) Stem: The main morpheme of the word, supplying the main meaning Fast Use

18、d very widely in Information Retrieval Run stemmer on keywords and the words in the documents,18,Part-Of-Speech(POS) Taggers,Part-Of-Speech: noun, verb, pronoun, etc. Brills Tagger HMM Tagger MXPOST,19,Brills Tagger,Transformation-Based Learning(TBL) tagger /projects/nlp/brill-pos-tagger First label

19、s every word with its most-likely tag Then Use Learned TBL Rules to correct mistakes Example: Change NN to VB when the previous tag is TO,20,HMM Tagger,Also called Maximum Likelihood Tagger Xerox PARCs HMM tagger: ftp:/ Choose the tag sequence with the maximum possibility given the words seen.,21,MX

20、POST: Maximum Entropy POS Tagger,Maximum Entropy Model is a framework integrating many information sources(called features) for classification Each candidate tag is a class Given features of the word(the around words, the morphological feature, and around tags, etc.), decide which class it belongs.,

21、22,Syntactic Parsers,Collins Parser XTAG MXPOST: Maximum Entropy Parser,23,Collins Parser,Context-free Grammar Use frequencies to solve ambiguities Got some idea of this parser Web-based Chart parser,24,XTAG,An on-going project to develop a wide-coverage grammar for English using a lexicalized Tree

22、Adjoining Grammar (TAG) formalism Context sensitive grammar consists of a parser, an X-windows grammar development interface and a morphological analyzer. /projects/nlp/xtag/,25,XTAG Contd,26,Semantic Knowledge Bases and Semantic Parser,Analyze what does it say WordNet Penn Treebank Web-based Semant

23、ic Parser,27,WordNet,Respresents lexical relationsUseful in word sense disambiguation,28,Penn Treebank,Predicate: fool(Kris),29,Semantic Parser,A web-based chart parser enriched with semantic constraints Example: Input: My dog has fleas. Output: has(my(dog),fleas),30,Speech Tools,ISIP EPOS CSLU Tool

24、kit,31,ISIP,ISIP(Institute for Signal and Information Processing) public domain speech recognition system Open research software Online courses, tutorials, dictionaries, databases Build your own speech recognition system,32,EPOS,a language independent rule-driven Text-to-Speech (TTS) system supports

25、 several main speech generation algorithms,33,CSLU Toolkit,Basic framework and tools for people to build, investigate and use interactive language systems speech recognition, natural language understanding, speech synthesis and facial animation technologies Easy to use , spread from higher education into homes,34,Thanks!,