syntactic processing parts of speech tagging
play

Syntactic Processing: Parts-of-Speech Tagging CSE354 - Spring 2020 - PowerPoint PPT Presentation

Syntactic Processing: Parts-of-Speech Tagging CSE354 - Spring 2020 Task Syntactic Processing Machine learning: h o w ? Parts-of-Speech Tagging Logistic regression Parts-of-Speech Open Class: Nouns, Verbs, Adjectives,


  1. Syntactic Processing: Parts-of-Speech Tagging CSE354 - Spring 2020

  2. Task ● Syntactic Processing ● Machine learning: h o w ? Parts-of-Speech Tagging ○ Logistic regression

  3. Parts-of-Speech Open Class: Nouns, Verbs, Adjectives, Adverbs

  4. Parts-of-Speech Open Class: Nouns, Verbs, Adjectives, Adverbs Function words: Determiners, conjunctions, pronouns, prepositions

  5. Parts-of-Speech: The Penn Treebank Tagset

  6. Parts-of-Speech: Social Media Tagset ( Gimpel et al., 2010)

  7. POS Tagging: Applications ● Resolving ambiguity (speech: “lead”) ● Shallow searching: find noun phrases ● Speed up parsing ● Use as feature (or in place of word)

  8. POS Tagging: Applications ● Resolving ambiguity (speech: “lead”) ● Shallow searching: find noun phrases ● Speed up parsing ● Use as feature (or in place of word) For this course: ● An introduction to language-based classification (logistic regression) ● Understand what modern deep learning methods are dealing with implicitly.

  9. Window-based POS Tagging The book looks brief so I am happy . ?

  10. Window-based POS Tagging The book looks brief so I am happy . D

  11. Window-based POS Tagging The book looks brief so I am happy . D N

  12. Window-based POS Tagging The book looks brief so I am happy . D N ?

  13. Window-based POS Tagging The book looks brief so I am happy . D N V

  14. Window-based POS Tagging The book looks brief so I am happy . D N V A

  15. Window-based POS Tagging The book looks brief so I am happy . D N V ?

  16. Window-based POS Tagging window size of 3 The book looks brief so I am happy . D N V ?

  17. Window-based POS Tagging window size of 3 The book looks brief so I am happy . D N V ?

  18. Window-based POS Tagging window size of 3 The book looks brief so I am happy . P(pos i = ‘N’|word i = “brief”) = 0.3 D N V ?

  19. Window-based POS Tagging window size of 3 The book looks brief so I am happy . P(pos i = ‘N’|word i = “brief”) = 0.3 D N V ? P(pos i = ‘V’|word i = “brief”) = 0.4 P(pos i = ‘A’|word i = “brief”) = 0.3

  20. Window-based POS Tagging window size of 3 The book looks brief so I am happy . P(p i =‘N’|w i =brief) = .30 D N V ? P(p i =‘V’|w i =brief) = .40 P(p i =‘A’|w i =brief) = .30

  21. Window-based POS Tagging window size of 3 The book looks brief so I am happy . P(p i =‘N’|w i =brief,w i-1 =looks,w i+1 =so) = ?? D N V ? P(p i =‘V’|w i =brief,w i-1 =looks,w i+1 =so) = ?? P(p i =‘A’|w i =brief,w i-1 =looks,w i+1 =so) = ??

  22. Window-based POS Tagging window size ideal result of 3 The book looks brief so I am happy . P(p i =‘N’|w i =brief,w i-1 =looks,w i+1 =so) = .005 D N V ? P(p i =‘V’|w i =brief,w i-1 =looks,w i+1 =so) = .005 P(p i =‘A’|w i =brief,w i-1 =looks,w i+1 =so) = .99

  23. Window-based POS Tagging More likely, because we window size haven’t seen of 3 this context before. The book looks brief so I am happy . P(p i =‘N’|w i =brief,w i-1 =looks,w i+1 =so) = .3 D N V ? P(p i =‘V’|w i =brief,w i-1 =looks,w i+1 =so) = .4 P(p i =‘A’|w i =brief,w i-1 =looks,w i+1 =so) = .3

  24. Window-based POS Tagging More likely, because we window size haven’t seen of 3 this context before. The book looks brief so I am happy . P(p i =‘N’|w i =brief,w i-1 =looks,w i+1 =so) = .3 D N V ? P(p i =‘V’|w i =brief,w i-1 =looks,w i+1 =so) = .4 P(p i =‘A’|w i =brief,w i-1 =looks,w i+1 =so) = .3

  25. Sequential Model window size of 3 The book looks brief so I am happy . P(p i =‘N’|w i =brief,w i-1 =looks,w i+1 =so) = .3 D N V ? P(p i =‘V’|w i =brief,w i-1 =looks,w i+1 =so) = .4 P(p i =‘A’|w i =brief,w i-1 =looks,w i+1 =so) = .3 sequence order of 1

  26. Sequential Model window size of 3 The book looks brief so I am happy . P(p i =‘N’|w i =brief,w i-1 =looks,w i+1 =so) = .3 D N V ? P(p i =‘V’|w i =brief,w i-1 =looks,w i+1 =so) = .4 P(p i =‘A’|w i =brief,w i-1 =looks,w i+1 =so) = .3 sequence order of 1

  27. Sequential Model window size of 3 The book looks brief so I am happy . P(p i =‘N’|p i-1 =V) = .4 D N V ? P(p i =‘V’|p i-1 =V) = .10 P(p i =‘A’|p i-1 =V) = .4 sequence order of 1

  28. Sequential Model window size of 3 The book looks brief so I am happy . P(p i =‘N’|p i-1 =V,w i =brief) = .3 D N V ? P(p i =‘V’|p i-1 =V,w i =brief) = .05 P(p i =‘A’|p i-1 =V,w i =brief) = .65 sequence order of 1

  29. Sequence modeling -- Tasks that in which a current label is dependent on previous labels within a sequence. More generally: tasks that can leverage the order of words. Most basic example: Language Modeling -- Predicting the next word given previous.

Recommend


More recommend