Download presentation
Presentation is loading. Please wait.
Published byEmmeline Pierce Modified over 9 years ago
1
Stanford POS tagger 17 th February 2011
2
System requirement Java 1.5+ – http://www.java.com/en/download/index.jsp http://www.java.com/en/download/index.jsp
3
Part-of-speech name abbreviations The Penn Treebank English POS tag set 1. CCCoordinating conjunction25. TOto 2. CDCardinal number26. UHInterjection 3. DTDeterminer27. VBVerb,base form 4. EXExistential there28. VBDVerb, past tense 5. FWForeignword29. VBGVerb,gerund/present 6. INPreposition/subordinating participle conjunction30. VBNVerb, past participle 7. JJAdjective31. VBPVerb, non-3rd ps. sing. present 8. JJRAdjective,comparative32. VBZVerb,3rd ps. sing. present 9. JJSAdjective, superlative33. WDTwh-determiner 10. LSListitem marker34. WPwh-pronoun 11. MDModal35. WP$Possessive wh-pronoun 12. NNNoun, singular or mass36. WRBwh-adverb 13. NNSNoun, plural37. #Pound sign 14. NNPProper noun, singular38. $Dollar sign 15. NNPSProper noun, plural39..Sentence-finalpunctuation 16. PDTPredeterminer40.,Comma 17. POSPossessive ending41. :Colon, semi-colon 18. PRPPersonal pronoun42. (Left bracket character 19. PP$Possessive pronoun43. )Right bracket character 20. RBAdverb44. "Straight double quote 21. RBRAdverb, comparative45. 'Leftopen single quote 22. RBSAdverb, superlative46. "Leftopen double quote 23. RPParticle47. 'Right close single quote 24. SYMSymbol (mathematical or scientific)48. "Right closedouble quote
4
Download http://nlp.stanford.edu/software/stanford- postagger-2010-05-26.tgz http://nlp.stanford.edu/software/stanford- postagger-2010-05-26.tgz
5
GUI
7
Command 1.generate a default properties file. 2.Tag file.
8
generate a default properties file command java -classpath stanford-postagger.jar edu.stanford.nlp.tagger.maxent.MaxentTagger -genprops > myPropsFile.prop
9
Tag file command java -mx300m -classpath stanford- postagger.jar edu.stanford.nlp.tagger.maxent.MaxentTagger -model models/bidirectional-distsim-wsj-0- 18.tagger -textFile sample-input.txt > sample- tagged.txt
10
Command
11
Result sample-input.txt The School of Liberal Arts was originally the Department of Language and Social Studies under the Faculty of Industrial Education. sample-tagged.txt The_DT School_NN of_IN Liberal_JJ Arts_NNS was_VBD originally_RB the_DT Department_NNP of_IN Language_NNP and_CC Social_NNP Studies_NNP under_IN the_DT Faculty_NNP of_IN Industrial_NNP Education_NNP._.
12
Q&A
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.