SlideShare a Scribd company logo
Overview of Machine Learning  for NLP Tasks: part I (based partly on slides by  Kevin Small and Scott Yih)
Goals of Introduction ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Overview ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Context Sensitive Spelling [2] ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Part of Speech (POS) Tagging ,[object Object],[object Object],[object Object]
Phrase Tagging ,[object Object],[object Object],[object Object]
Some Other Tasks ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
[object Object]
Learning Mapping Functions ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Multi-class Classification [3,4] One Versus All (OvA) Constraint Classification
Online Learning [5] ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
[object Object]
Defining Learning Problems [6] ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Context Sensitive Spelling ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
What are ‘feature’, ‘feature type’, anyway? ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Preprocessing: cleaning up and enriching text ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Download Some Tools ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Preprocessing scripts ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Problems running .pl scripts? ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Minor Problems with install ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
[object Object]
A Machine Learning System Testing Examples Feature Vectors Training Examples Preprocessing Feature Extraction Machine Learner Classifier(s) Inference Raw Text Formatted Text Function Parameters Labels Labels
Preprocessing Text ,[object Object],[object Object],They recently recovered a small piece of a live Elvis concert recording. He was singing gospel songs, including “Peace in the Valley.”  0  0  0  They 0  0  1  recently 0  0  2  recovered 0  0  3  a 0  0  4  small piece  0  5  piece 0  0  6  of : 0  1  6  including 0  1  7  QUOTE peace 1  8  Peace 0  1  9  in 0  1  10  the 0  1  11  Valley 0  1  12  . 0  1  13  QUOTE
A Machine Learning System Feature Vectors Preprocessing Feature Extraction Raw Text Formatted Text
[object Object]
Feature Extraction with FEX ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Feature Extraction ,[object Object],[object Object],0  0  0  They 0  0  1  recently 0  0  2  recovered 0  0  3  a 0  0  4  small piece  0  5  piece 0  0  6  of : 0  1  6  including 0  1  7  QUOTE peace 1  8  Peace 0  1  9  in 0  1  10  the 0  1  11  Valley 0  1  12  . 0  1  13  QUOTE 0, 1001, 1013, 1134, 1175, 1206 1, 1021, 1055, 1085, 1182, 1252 Lexicon File
Role of FEX ,[object Object],[object Object],1,  1001,  1003,  1004, 1006: 2,  1002,  1003,  1005, 1006: Feature Extraction FEX lab[accept], w[you], w[the], w[you*], w[*the] lab[except],  w[her], w[the], w[her*], w[*the]
Four Important Files FEX A new representation of the raw text data ,[object Object],[object Object],Feature vectors for SNoW Mapping of feature and feature id Script Corpus Example Lexicon
Corpus – General Linear Format ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Corpus –  Context Sensitive Spelling ,[object Object],[object Object],[object Object],[object Object]
Script –  Means of Feature Engineering ,[object Object],[object Object],[object Object]
Script –  Description of Feature Types ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Graphical Representation 0 1 2 3 4 5 6 7 Target -2 -1 1 2 0 -3 -4 3 Window [-2,2] Why WRB won VBD 't NN you PRP accept VBP the DT facts NNS ? .
Script – Syntax ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Basic RGF’s – Sensors (1/2) ,[object Object],[object Object],len[5] length of the word len Length v[eager] active if the word starts with a vowel v Vowel t[NNP] part-of-speech tag t Tag w[you] the word (spelling) w Word Example Interpretation Mnemonic Type
Basic RGF’s – Sensors (2/2) ,[object Object],[object Object],More sensors can be found by looking at FEX source (Sensors.h) ,[object Object],isCity[Chicago] active is the phrase is the name of a city isCity City List vCls[51.2] return Levin’s verb class vCls Verb Class Example Interpretation Mnemonic Type
Complex RGF’s ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
(Sparse) Collocation 0 1 2 3 4 5 6 7 Target -2 -1 1 2 0 -3 -4 3 -1 inc: coloc(w,t)[-2,2] w[‘t]-t[PRP], w[you]-t[VBP] w[accept]-t[DT], w[the]-t[NNS] -1 inc: scoloc(w,t)[-2,2] w[‘t]-t[PRP], w[‘t]-t[VBP], w[‘t]-t[DT], w[‘t]-t[NNS], w[you]-t[VBP], w[you]-t[DT], w[you]-t[NNS], w[accept]-t[DT], w[accept]-t[NNS],  w[the]-t[NNS] Why WRB won VBD 't NN you PRP accept VBP the DT facts NNS ? .
Examples – 2 Scripts ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Lexicon & Example (1/3) ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],Generated by  w[-1,1] Feature indices of  lab  start from 1. Feature indices of regular features start from 1001. Generated by  lab(w)
Lexicon & Example (2/3) ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],We treat  only  these two words as  targets .
Lexicon & Example (3/3) ,[object Object],[object Object],[object Object],[object Object],[object Object]
[object Object],[object Object]
Citations ,[object Object],[object Object],[object Object],[object Object],[object Object]
Citations ,[object Object],[object Object],[object Object],[object Object]

More Related Content

What's hot

Introduction to programming with python
Introduction to programming with pythonIntroduction to programming with python
Introduction to programming with python
Porimol Chandro
 
1. python programming
1. python programming1. python programming
1. python programming
sreeLekha51
 
introduction to python
 introduction to python introduction to python
introduction to python
Jincy Nelson
 
Python Presentation
Python PresentationPython Presentation
Python Presentation
Narendra Sisodiya
 
8 issues in pos tagging
8 issues in pos tagging8 issues in pos tagging
8 issues in pos tagging
ThennarasuSakkan
 
11 Unit 1 Chapter 02 Python Fundamentals
11  Unit 1 Chapter 02 Python Fundamentals11  Unit 1 Chapter 02 Python Fundamentals
11 Unit 1 Chapter 02 Python Fundamentals
Praveen M Jigajinni
 
Introduction to prolog
Introduction to prologIntroduction to prolog
Introduction to prolog
Harry Potter
 
Fundamentals of Python Programming
Fundamentals of Python ProgrammingFundamentals of Python Programming
Fundamentals of Python Programming
Kamal Acharya
 
Get started python programming part 1
Get started python programming   part 1Get started python programming   part 1
Get started python programming part 1
Nicholas I
 
Python Interview questions 2020
Python Interview questions 2020Python Interview questions 2020
Python Interview questions 2020
VigneshVijay21
 
Python Tutorial Part 1
Python Tutorial Part 1Python Tutorial Part 1
Python Tutorial Part 1
Haitham El-Ghareeb
 
Relationship Among Token, Lexeme & Pattern
Relationship Among Token, Lexeme & PatternRelationship Among Token, Lexeme & Pattern
Relationship Among Token, Lexeme & Pattern
Bharat Rathore
 
SE Michigan PowerShell Users Group - Regex Part1
SE Michigan PowerShell Users Group -  Regex Part1SE Michigan PowerShell Users Group -  Regex Part1
SE Michigan PowerShell Users Group - Regex Part1
Southeast Michigan PowerShell Script Club
 
R P G Generator
R P G  GeneratorR P G  Generator
R P G Generator
cfministries
 
Nltk - Boston Text Analytics
Nltk - Boston Text AnalyticsNltk - Boston Text Analytics
Nltk - Boston Text Analytics
shanbady
 
Introduction to Python
Introduction to Python Introduction to Python
Introduction to Python
amiable_indian
 
Andy On Closures
Andy On ClosuresAndy On Closures
Andy On Closures
melbournepatterns
 
Traits: A New Language Feature for PHP?
Traits: A New Language Feature for PHP?Traits: A New Language Feature for PHP?
Traits: A New Language Feature for PHP?
Stefan Marr
 
Reversing Google Protobuf protocol
Reversing Google Protobuf protocolReversing Google Protobuf protocol
Reversing Google Protobuf protocol
n|u - The Open Security Community
 

What's hot (20)

Introduction to programming with python
Introduction to programming with pythonIntroduction to programming with python
Introduction to programming with python
 
1. python programming
1. python programming1. python programming
1. python programming
 
introduction to python
 introduction to python introduction to python
introduction to python
 
Python Presentation
Python PresentationPython Presentation
Python Presentation
 
8 issues in pos tagging
8 issues in pos tagging8 issues in pos tagging
8 issues in pos tagging
 
11 Unit 1 Chapter 02 Python Fundamentals
11  Unit 1 Chapter 02 Python Fundamentals11  Unit 1 Chapter 02 Python Fundamentals
11 Unit 1 Chapter 02 Python Fundamentals
 
Introduction to prolog
Introduction to prologIntroduction to prolog
Introduction to prolog
 
Fundamentals of Python Programming
Fundamentals of Python ProgrammingFundamentals of Python Programming
Fundamentals of Python Programming
 
Get started python programming part 1
Get started python programming   part 1Get started python programming   part 1
Get started python programming part 1
 
Python Interview questions 2020
Python Interview questions 2020Python Interview questions 2020
Python Interview questions 2020
 
Python Tutorial Part 1
Python Tutorial Part 1Python Tutorial Part 1
Python Tutorial Part 1
 
Relationship Among Token, Lexeme & Pattern
Relationship Among Token, Lexeme & PatternRelationship Among Token, Lexeme & Pattern
Relationship Among Token, Lexeme & Pattern
 
SE Michigan PowerShell Users Group - Regex Part1
SE Michigan PowerShell Users Group -  Regex Part1SE Michigan PowerShell Users Group -  Regex Part1
SE Michigan PowerShell Users Group - Regex Part1
 
R P G Generator
R P G  GeneratorR P G  Generator
R P G Generator
 
 
Nltk - Boston Text Analytics
Nltk - Boston Text AnalyticsNltk - Boston Text Analytics
Nltk - Boston Text Analytics
 
Introduction to Python
Introduction to Python Introduction to Python
Introduction to Python
 
Andy On Closures
Andy On ClosuresAndy On Closures
Andy On Closures
 
Traits: A New Language Feature for PHP?
Traits: A New Language Feature for PHP?Traits: A New Language Feature for PHP?
Traits: A New Language Feature for PHP?
 
Reversing Google Protobuf protocol
Reversing Google Protobuf protocolReversing Google Protobuf protocol
Reversing Google Protobuf protocol
 

Viewers also liked

Mahout Tutorial FOSSMEET NITC
Mahout Tutorial FOSSMEET NITCMahout Tutorial FOSSMEET NITC
Mahout Tutorial FOSSMEET NITC
Jaganadh Gopinadhan
 
Query Linguistic Intent Detection
Query Linguistic Intent DetectionQuery Linguistic Intent Detection
Query Linguistic Intent Detection
butest
 
Machine Learning for NLP
Machine Learning for NLPMachine Learning for NLP
Machine Learning for NLP
butest
 
NLP & Machine Learning - An Introductory Talk
NLP & Machine Learning - An Introductory Talk NLP & Machine Learning - An Introductory Talk
NLP & Machine Learning - An Introductory Talk
Vijay Ganti
 
Deeplearning NLP
Deeplearning NLPDeeplearning NLP
Deeplearning NLP
Francesco Gadaleta
 
Introduction to Natural Language Processing
Introduction to Natural Language ProcessingIntroduction to Natural Language Processing
Introduction to Natural Language Processing
Pranav Gupta
 

Viewers also liked (6)

Mahout Tutorial FOSSMEET NITC
Mahout Tutorial FOSSMEET NITCMahout Tutorial FOSSMEET NITC
Mahout Tutorial FOSSMEET NITC
 
Query Linguistic Intent Detection
Query Linguistic Intent DetectionQuery Linguistic Intent Detection
Query Linguistic Intent Detection
 
Machine Learning for NLP
Machine Learning for NLPMachine Learning for NLP
Machine Learning for NLP
 
NLP & Machine Learning - An Introductory Talk
NLP & Machine Learning - An Introductory Talk NLP & Machine Learning - An Introductory Talk
NLP & Machine Learning - An Introductory Talk
 
Deeplearning NLP
Deeplearning NLPDeeplearning NLP
Deeplearning NLP
 
Introduction to Natural Language Processing
Introduction to Natural Language ProcessingIntroduction to Natural Language Processing
Introduction to Natural Language Processing
 

Similar to ppt

Nltk
NltkNltk
Nltk
Anirudh
 
NLP Deep Learning with Tensorflow
NLP Deep Learning with TensorflowNLP Deep Learning with Tensorflow
NLP Deep Learning with Tensorflow
seungwoo kim
 
Text classification-php-v4
Text classification-php-v4Text classification-php-v4
Text classification-php-v4
Glenn De Backer
 
Day2-Slides.ppt pppppppppppppppppppppppppp
Day2-Slides.ppt ppppppppppppppppppppppppppDay2-Slides.ppt pppppppppppppppppppppppppp
Day2-Slides.ppt pppppppppppppppppppppppppp
ratnapatil14
 
Feature Engineering for NLP
Feature Engineering for NLPFeature Engineering for NLP
Feature Engineering for NLP
Bill Liu
 
NLP
NLPNLP
Open nlp presentationss
Open nlp presentationssOpen nlp presentationss
Open nlp presentationss
Chandan Deb
 
Dsm as theory building
Dsm as theory buildingDsm as theory building
Dsm as theory building
ClarkTony
 
Industrial strength - Natural Language Processing
Industrial strength - Natural Language ProcessingIndustrial strength - Natural Language Processing
Industrial strength - Natural Language Processing
Jeffrey Williams
 
Similarity computation exploiting the semantic and syntactic inherent structu...
Similarity computation exploiting the semantic and syntactic inherent structu...Similarity computation exploiting the semantic and syntactic inherent structu...
Similarity computation exploiting the semantic and syntactic inherent structu...
Joydeep Mondal
 
Text Mining Infrastructure in R
Text Mining Infrastructure in RText Mining Infrastructure in R
Text Mining Infrastructure in R
Ashraf Uddin
 
Machine Learning Applications in NLP.ppt
Machine Learning Applications in NLP.pptMachine Learning Applications in NLP.ppt
Machine Learning Applications in NLP.ppt
butest
 
Erlang session1
Erlang session1Erlang session1
Erlang session1
mohamedsamyali
 
Natural Language Processing (NLP)
Natural Language Processing (NLP)Natural Language Processing (NLP)
Natural Language Processing (NLP)
Yuriy Guts
 
Sk t academy lecture note
Sk t academy lecture noteSk t academy lecture note
Sk t academy lecture note
Susang Kim
 
Tools for the Toolmakers
Tools for the ToolmakersTools for the Toolmakers
Tools for the Toolmakers
Caleb Callaway
 
Designing A Syntax Based Retrieval System03
Designing A Syntax Based Retrieval System03Designing A Syntax Based Retrieval System03
Designing A Syntax Based Retrieval System03
Avelin Huo
 
Poetic APIs
Poetic APIsPoetic APIs
Poetic APIs
Erik Rose
 
Natural language processing: feature extraction
Natural language processing: feature extractionNatural language processing: feature extraction
Natural language processing: feature extraction
Gabriel Hamilton
 
C++ Notes by Hisham Ahmed Rizvi for Class 12th Board Exams
C++ Notes by Hisham Ahmed Rizvi for Class 12th Board ExamsC++ Notes by Hisham Ahmed Rizvi for Class 12th Board Exams
C++ Notes by Hisham Ahmed Rizvi for Class 12th Board Exams
hishamrizvi
 

Similar to ppt (20)

Nltk
NltkNltk
Nltk
 
NLP Deep Learning with Tensorflow
NLP Deep Learning with TensorflowNLP Deep Learning with Tensorflow
NLP Deep Learning with Tensorflow
 
Text classification-php-v4
Text classification-php-v4Text classification-php-v4
Text classification-php-v4
 
Day2-Slides.ppt pppppppppppppppppppppppppp
Day2-Slides.ppt ppppppppppppppppppppppppppDay2-Slides.ppt pppppppppppppppppppppppppp
Day2-Slides.ppt pppppppppppppppppppppppppp
 
Feature Engineering for NLP
Feature Engineering for NLPFeature Engineering for NLP
Feature Engineering for NLP
 
NLP
NLPNLP
NLP
 
Open nlp presentationss
Open nlp presentationssOpen nlp presentationss
Open nlp presentationss
 
Dsm as theory building
Dsm as theory buildingDsm as theory building
Dsm as theory building
 
Industrial strength - Natural Language Processing
Industrial strength - Natural Language ProcessingIndustrial strength - Natural Language Processing
Industrial strength - Natural Language Processing
 
Similarity computation exploiting the semantic and syntactic inherent structu...
Similarity computation exploiting the semantic and syntactic inherent structu...Similarity computation exploiting the semantic and syntactic inherent structu...
Similarity computation exploiting the semantic and syntactic inherent structu...
 
Text Mining Infrastructure in R
Text Mining Infrastructure in RText Mining Infrastructure in R
Text Mining Infrastructure in R
 
Machine Learning Applications in NLP.ppt
Machine Learning Applications in NLP.pptMachine Learning Applications in NLP.ppt
Machine Learning Applications in NLP.ppt
 
Erlang session1
Erlang session1Erlang session1
Erlang session1
 
Natural Language Processing (NLP)
Natural Language Processing (NLP)Natural Language Processing (NLP)
Natural Language Processing (NLP)
 
Sk t academy lecture note
Sk t academy lecture noteSk t academy lecture note
Sk t academy lecture note
 
Tools for the Toolmakers
Tools for the ToolmakersTools for the Toolmakers
Tools for the Toolmakers
 
Designing A Syntax Based Retrieval System03
Designing A Syntax Based Retrieval System03Designing A Syntax Based Retrieval System03
Designing A Syntax Based Retrieval System03
 
Poetic APIs
Poetic APIsPoetic APIs
Poetic APIs
 
Natural language processing: feature extraction
Natural language processing: feature extractionNatural language processing: feature extraction
Natural language processing: feature extraction
 
C++ Notes by Hisham Ahmed Rizvi for Class 12th Board Exams
C++ Notes by Hisham Ahmed Rizvi for Class 12th Board ExamsC++ Notes by Hisham Ahmed Rizvi for Class 12th Board Exams
C++ Notes by Hisham Ahmed Rizvi for Class 12th Board Exams
 

More from butest

EL MODELO DE NEGOCIO DE YOUTUBE
EL MODELO DE NEGOCIO DE YOUTUBEEL MODELO DE NEGOCIO DE YOUTUBE
EL MODELO DE NEGOCIO DE YOUTUBE
butest
 
1. MPEG I.B.P frame之不同
1. MPEG I.B.P frame之不同1. MPEG I.B.P frame之不同
1. MPEG I.B.P frame之不同butest
 
LESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIALLESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIAL
butest
 
Timeline: The Life of Michael Jackson
Timeline: The Life of Michael JacksonTimeline: The Life of Michael Jackson
Timeline: The Life of Michael Jackson
butest
 
Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...
Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...
Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...
butest
 
LESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIALLESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIAL
butest
 
Com 380, Summer II
Com 380, Summer IICom 380, Summer II
Com 380, Summer II
butest
 
PPT
PPTPPT
PPT
butest
 
The MYnstrel Free Press Volume 2: Economic Struggles, Meet Jazz
The MYnstrel Free Press Volume 2: Economic Struggles, Meet JazzThe MYnstrel Free Press Volume 2: Economic Struggles, Meet Jazz
The MYnstrel Free Press Volume 2: Economic Struggles, Meet Jazz
butest
 
MICHAEL JACKSON.doc
MICHAEL JACKSON.docMICHAEL JACKSON.doc
MICHAEL JACKSON.doc
butest
 
Social Networks: Twitter Facebook SL - Slide 1
Social Networks: Twitter Facebook SL - Slide 1Social Networks: Twitter Facebook SL - Slide 1
Social Networks: Twitter Facebook SL - Slide 1
butest
 
Facebook
Facebook Facebook
Facebook
butest
 
Executive Summary Hare Chevrolet is a General Motors dealership ...
Executive Summary Hare Chevrolet is a General Motors dealership ...Executive Summary Hare Chevrolet is a General Motors dealership ...
Executive Summary Hare Chevrolet is a General Motors dealership ...
butest
 
Welcome to the Dougherty County Public Library's Facebook and ...
Welcome to the Dougherty County Public Library's Facebook and ...Welcome to the Dougherty County Public Library's Facebook and ...
Welcome to the Dougherty County Public Library's Facebook and ...
butest
 
NEWS ANNOUNCEMENT
NEWS ANNOUNCEMENTNEWS ANNOUNCEMENT
NEWS ANNOUNCEMENT
butest
 
C-2100 Ultra Zoom.doc
C-2100 Ultra Zoom.docC-2100 Ultra Zoom.doc
C-2100 Ultra Zoom.doc
butest
 
MAC Printing on ITS Printers.doc.doc
MAC Printing on ITS Printers.doc.docMAC Printing on ITS Printers.doc.doc
MAC Printing on ITS Printers.doc.doc
butest
 
Mac OS X Guide.doc
Mac OS X Guide.docMac OS X Guide.doc
Mac OS X Guide.doc
butest
 
hier
hierhier
hier
butest
 
WEB DESIGN!
WEB DESIGN!WEB DESIGN!
WEB DESIGN!
butest
 

More from butest (20)

EL MODELO DE NEGOCIO DE YOUTUBE
EL MODELO DE NEGOCIO DE YOUTUBEEL MODELO DE NEGOCIO DE YOUTUBE
EL MODELO DE NEGOCIO DE YOUTUBE
 
1. MPEG I.B.P frame之不同
1. MPEG I.B.P frame之不同1. MPEG I.B.P frame之不同
1. MPEG I.B.P frame之不同
 
LESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIALLESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIAL
 
Timeline: The Life of Michael Jackson
Timeline: The Life of Michael JacksonTimeline: The Life of Michael Jackson
Timeline: The Life of Michael Jackson
 
Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...
Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...
Popular Reading Last Updated April 1, 2010 Adams, Lorraine The ...
 
LESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIALLESSONS FROM THE MICHAEL JACKSON TRIAL
LESSONS FROM THE MICHAEL JACKSON TRIAL
 
Com 380, Summer II
Com 380, Summer IICom 380, Summer II
Com 380, Summer II
 
PPT
PPTPPT
PPT
 
The MYnstrel Free Press Volume 2: Economic Struggles, Meet Jazz
The MYnstrel Free Press Volume 2: Economic Struggles, Meet JazzThe MYnstrel Free Press Volume 2: Economic Struggles, Meet Jazz
The MYnstrel Free Press Volume 2: Economic Struggles, Meet Jazz
 
MICHAEL JACKSON.doc
MICHAEL JACKSON.docMICHAEL JACKSON.doc
MICHAEL JACKSON.doc
 
Social Networks: Twitter Facebook SL - Slide 1
Social Networks: Twitter Facebook SL - Slide 1Social Networks: Twitter Facebook SL - Slide 1
Social Networks: Twitter Facebook SL - Slide 1
 
Facebook
Facebook Facebook
Facebook
 
Executive Summary Hare Chevrolet is a General Motors dealership ...
Executive Summary Hare Chevrolet is a General Motors dealership ...Executive Summary Hare Chevrolet is a General Motors dealership ...
Executive Summary Hare Chevrolet is a General Motors dealership ...
 
Welcome to the Dougherty County Public Library's Facebook and ...
Welcome to the Dougherty County Public Library's Facebook and ...Welcome to the Dougherty County Public Library's Facebook and ...
Welcome to the Dougherty County Public Library's Facebook and ...
 
NEWS ANNOUNCEMENT
NEWS ANNOUNCEMENTNEWS ANNOUNCEMENT
NEWS ANNOUNCEMENT
 
C-2100 Ultra Zoom.doc
C-2100 Ultra Zoom.docC-2100 Ultra Zoom.doc
C-2100 Ultra Zoom.doc
 
MAC Printing on ITS Printers.doc.doc
MAC Printing on ITS Printers.doc.docMAC Printing on ITS Printers.doc.doc
MAC Printing on ITS Printers.doc.doc
 
Mac OS X Guide.doc
Mac OS X Guide.docMac OS X Guide.doc
Mac OS X Guide.doc
 
hier
hierhier
hier
 
WEB DESIGN!
WEB DESIGN!WEB DESIGN!
WEB DESIGN!
 

ppt

  • 1. Overview of Machine Learning for NLP Tasks: part I (based partly on slides by Kevin Small and Scott Yih)
  • 2.
  • 3.
  • 4.
  • 5.
  • 6.
  • 7.
  • 8.
  • 9.
  • 10. Multi-class Classification [3,4] One Versus All (OvA) Constraint Classification
  • 11.
  • 12.
  • 13.
  • 14.
  • 15.
  • 16.
  • 17.
  • 18.
  • 19.
  • 20.
  • 21.
  • 22. A Machine Learning System Testing Examples Feature Vectors Training Examples Preprocessing Feature Extraction Machine Learner Classifier(s) Inference Raw Text Formatted Text Function Parameters Labels Labels
  • 23.
  • 24. A Machine Learning System Feature Vectors Preprocessing Feature Extraction Raw Text Formatted Text
  • 25.
  • 26.
  • 27.
  • 28.
  • 29.
  • 30.
  • 31.
  • 32.
  • 33.
  • 34. Graphical Representation 0 1 2 3 4 5 6 7 Target -2 -1 1 2 0 -3 -4 3 Window [-2,2] Why WRB won VBD 't NN you PRP accept VBP the DT facts NNS ? .
  • 35.
  • 36.
  • 37.
  • 38.
  • 39. (Sparse) Collocation 0 1 2 3 4 5 6 7 Target -2 -1 1 2 0 -3 -4 3 -1 inc: coloc(w,t)[-2,2] w[‘t]-t[PRP], w[you]-t[VBP] w[accept]-t[DT], w[the]-t[NNS] -1 inc: scoloc(w,t)[-2,2] w[‘t]-t[PRP], w[‘t]-t[VBP], w[‘t]-t[DT], w[‘t]-t[NNS], w[you]-t[VBP], w[you]-t[DT], w[you]-t[NNS], w[accept]-t[DT], w[accept]-t[NNS], w[the]-t[NNS] Why WRB won VBD 't NN you PRP accept VBP the DT facts NNS ? .
  • 40.
  • 41.
  • 42.
  • 43.
  • 44.
  • 45.
  • 46.

Editor's Notes

  1. Pos, spelling
  2. Task is relevant because words can take multiple POS tags, correct one determined by context.
  3. again, issue of: multiple representations, ambiguity (JFK) ‘ harder’ task, because phrase level
  4. (in a principled way, given ML theory, that is...)
  5. Just to r^d -> r, instance space, output space, single (multi) label
  6. pictures of a 4 class classifier...with the OvA definition
  7. Learning a Linear Discriminant Function in Online
  8. (in a principled way, given ML theory, that is...)
  9. Well-posed learning problems
  10. Framing the classification task
  11. POS tagger requires one sentence per line.
  12. A machine learning system
  13. Preprocessing text
  14. A machine learning system
  15. Feature Generation (Kernels)
  16. today, we’re focusing on the second form. 3 rd form is deprecated
  17. Emphasize that it provides you a means to define the types of features you like Feature engineering is in fact an important part of practice We’ll generate two versions of examples using two different script files
  18. Emphasize that it provides you a means to define the types of features you like Feature engineering is in fact an important part of practice We’ll generate two versions of examples using two different script files
  19. CS spelling: do we want features that include the target word itself?
  20. generates active features -> if the pattern isn’t there, no feature generated.
  21. disjunction: a shorthand unless combined with e.g. existential; w|t is a bit silly
  22. Note: don’t have ‘inc’ – don’t want target word to be part of the example (because if other word is subsituted in a mistake in test example, your features won’t fire!)