1. SIMS 290-2: Applied Natural Language Processing
Barbara Rosario
Sept 27, 2004

2. Today Classification Various issues regarding classification
Text categorization (and other applications)
Various issues regarding classification
Clustering vs. classification, binary vs. multi-way, flat vs. hierarchical classification…
Introduce the steps necessary for a classification task
Define classes
Label text
Features
Training and evaluation of a classifier

3. Classification
Goal: Assign ‘objects’ from a universe to two or more classes or categories
Examples:
Problem Object Categories
Tagging Word POS
Sense Disambiguation Word The word’s senses
Information retrieval Document Relevant/not relevant
Sentiment classification Document Positive/negative
Author identification Document Authors
From: Foundations of Statistical Natural Language Processing. Manning and Schutze

4. Author identification
They agreed that Mrs. X should only hear of the departure of the family, without being alarmed on the score of the gentleman's conduct; but even this partial communication gave her a great deal of concern, and she bewailed it as exceedingly unlucky that the ladies should happen to go away, just as they were all getting so intimate together.
Gas looming through the fog in divers places in the streets, much as the sun may, from the spongey fields, be seen to loom by husbandman and ploughboy. Most of the shops lighted two hours before their time--as the gas seems to know, for it has a haggard and unwilling look. The raw afternoon is rawest, and the dense fog is densest, and the muddy streets are muddiest near that leaden-headed old obstruction, appropriate ornament for the threshold of a leaden-headed old corporation, Temple Bar.
Mrs. Bennet

5. Author identification
Jane Austen ( ), Pride and Prejudice
Charles Dickens ( ), Bleak House

6. Author identification
Federalist papers
77 short essays written in by Hamilton, Jay and Madison to persuade NY to ratify the US Constitution; published under a pseudonym
The authorships of 12 papers was in dispute (disputed papers)
In 1964 Mosteller and Wallace* solved the problem
They identified 70 function words as good candidates for authorships analysis
Using statistical inference they concluded the author was Madison
Mosteller, Frederick and Wallace, David L Inference and Disputed Authorship: The Federalist.

7. Function words for Author Identification

8. Function words for Author Identification

9. Classification
Goal: Assign ‘objects’ from a universe to two or more classes or categories
Examples:
Problem Object Categories
Author identification Document Authors
Language identification Document Language
From: Foundations os Statistical Natural Language Processing. Manning and Schutze

10. Language identification
Tutti gli esseri umani nascono liberi ed eguali in dignità e diritti. Essi sono dotati di ragione e di coscienza e devono agire gli uni verso gli altri in spirito di fratellanza.
Alle Menschen sind frei und gleich an Würde und Rechten geboren. Sie sind mit Vernunft und Gewissen begabt und sollen einander im Geist der Brüderlichkeit begegnen.
Universal Declaration of Human Rights, UN, in 363 languages

11. Language identification
égaux
eguali
iguales
edistämään Ü

12. Classification
Goal: Assign ‘objects’ from a universe to two or more classes or categories
Examples:
Problem Object Categories
Author identification Document Authors
Language identification Document Language
Text categorization Document Topics
From: Foundations of Statistical Natural Language Processing. Manning and Schutze

13. Text categorization
Topic categorization: classify the document into semantics topics
The U.S. swept into the Davis Cup final on Saturday when twins Bob and Mike Bryan defeated Belarus's Max Mirnyi and Vladimir Voltchkov to give the Americans an unsurmountable 3-0 lead in the best-of-five semi-final tie.
One of the strangest, most relentless hurricane seasons on record reached new bizarre heights yesterday as the plodding approach of Hurricane Jeanne prompted evacuation orders for hundreds of thousands of Floridians and high wind warnings that stretched 350 miles from the swamp towns south of Miami to the historic city of St. Augustine.

14. Text categorization http://news.google.com/ Reuters
Collection of (21,578) newswire documents.
For research purposes: a standard text collection to compare systems and algorithms
135 valid topics categories

15. Reuters
Top topics in Reuters

16. Reuters
<REUTERS TOPICS="YES" LEWISSPLIT="TRAIN" CGISPLIT="TRAINING-SET" OLDID="12981" NEWID="798">
<DATE> 2-MAR :51:43.42</DATE>
<TOPICS><D>livestock</D><D>hog</D></TOPICS>
<TITLE>AMERICAN PORK CONGRESS KICKS OFF TOMORROW</TITLE>
<DATELINE> CHICAGO, March 2 - </DATELINE><BODY>The American Pork Congress kicks off
tomorrow, March 3, in Indianapolis with 160 of the nations pork producers from 44 member states determining industry positions on a number of issues, according to the National Pork Producers Council, NPPC.
Delegates to the three day Congress will be considering 26 resolutions concerning various issues, including the future direction of farm policy and the tax law as it applies to the agriculture sector. The delegates will also debate whether to endorse concepts of a national PRV (pseudorabies virus) control and eradication program, the NPPC said.
A large trade show, in conjunction with the congress, will feature the latest in technology in all areas of the industry, the NPPC added. Reuter
</BODY></TEXT></REUTERS>

17. Text categorization: examples
Topic categorization
Reuters.
Spam filtering
Determine if a mail message is spam (or not)
Customer service message classification

18. Classification vs. Clustering
Classification assumes labeled data: we know how many classes there are and we have examples for each class (labeled data).
Classification is supervised
In Clustering we don’t have labeled data; we just assume that there is a natural division in the data and we may not know how many divisions (clusters) there are
Clustering is unsupervised

19. Classification
Class1
Class2

20. Classification
Class1
Class2

21. Classification
Class1
Class2

22. Classification
Class1
Class2

23. Clustering

24. Clustering

25. Clustering

26. Clustering

27. Clustering

28. Categories (Labels, Classes)
Labeling data
2 problems:
Decide the possible classes (which ones, how many)
Domain and application dependent
Label text
Difficult, time consuming, inconsistency between annotators

29. Reuters Why not topic = policy ?
<REUTERS TOPICS="YES" LEWISSPLIT="TRAIN" CGISPLIT="TRAINING-SET" OLDID="12981" NEWID="798">
<DATE> 2-MAR :51:43.42</DATE>
<TOPICS><D>livestock</D><D>hog</D></TOPICS>
<TITLE>AMERICAN PORK CONGRESS KICKS OFF TOMORROW</TITLE>
<DATELINE> CHICAGO, March 2 - </DATELINE><BODY>The American Pork Congress kicks off
tomorrow, March 3, in Indianapolis with 160 of the nations pork producers from 44 member states determining industry positions on a number of issues, according to the National Pork Producers Council, NPPC.
Delegates to the three day Congress will be considering 26 resolutions concerning various issues, including the future direction of farm policy and the tax law as it applies to the agriculture sector. The delegates will also debate whether to endorse concepts of a national PRV (pseudorabies virus) control and eradication program, the NPPC said.
A large trade show, in conjunction with the congress, will feature the latest in technology in all areas of the industry, the NPPC added. Reuter
</BODY></TEXT></REUTERS>
Why not topic = policy ?

30. Binary vs. multi-way classification
Binary classification: two classes
Multi-way classification: more than two classes
Sometime it can be convenient to treat a multi-way problem like a binary one: one class versus all the others, for all classes

31. Flat vs. Hierarchical classification
Flat classification: relations between the classes undetermined
Hierarchical classification: hierarchy where each node is the sub-class of its parent’s node

32. Single- vs. multi-category classification
In single-category text classification each text belongs to exactly one category
In multi-category text classification, each text can have zero or more categories

33. LabeledText class in NLTK
>>> text = "Seven-time Formula One champion Michael Schumacher took on the Shanghai circuit Saturday in qualifying for the first Chinese Grand Prix."
>>> label = “sport”
>>> labeled_text = LabeledText(text, label)
>>> labeled_text.text()
“Seven-time Formula One champion Michael Schumacher took on the Shanghai circuit Saturday in qualifying for the first Chinese Grand Prix.”
>>> labeled_text.label()
“sport”

34. NLTK: The Classifier Interface
classify determines which label is most appropriate for a given text token, and returns a labeled text token with that label.
labels returns the list of category labels that are used by the classifier.
>>> token = Token(“The World Health Organization is recommending more importance be attached to the prevention of heart disease and other cardiovascular ailments rather than focusing on treatment.”)
>>> my_classifier.classify(token)
“The World Health Organization is recommending more importance be attached to the prevention of heart disease and other cardiovascular ailments rather than focusing on treatment.”/ health
>>> my_classifier.labels()
("sport", "health", "world",…)

35. Features Here the classification takes as input the whole string
>>> text = "Seven-time Formula One champion Michael Schumacher took on the Shanghai circuit Saturday in qualifying for the first Chinese Grand Prix."
>>> label = “sport”
>>> labeled_text = LabeledText(text, label)
Here the classification takes as input the whole string
What’s the problem with that?
What are the features that could be useful for this example?

36. Feature terminology
Feature: An aspect of the text that is relevant to the task
Some typical features
Words present in text
Frequency of words
Capitalization
Are there NE?
WordNet
Others?

37. Feature terminology
Feature: An aspect of the text that is relevant to the task
Feature value: the realization of the feature in the text
Words present in text : Kerry, Schumacher, China…
Frequency of word: Kerry(10), Schumacher(1)…
Are there dates? Yes/no
Are there PERSONS? Yes/no
Are there ORGANIZATIONS? Yes/no
WordNet: Holonyms (China is part of Asia), Synonyms(China, People's Republic of China, mainland China)

38. Feature Types Boolean (or Binary) Features
Features that generate boolean (binary) values.
Boolean features are the simplest and the most common type of feature.
f1(text) = 1 if text contain “Kerry”
0 otherwise
f2(text) = 1 if text contain PERSON

39. Feature Types Integer Features Features that generate integer values.
Integer features can be used to give classifiers access to more precise information about the text.
f1(text) = Number of times text contains “Kerry”
f2(text) = Number of times text contains PERSON

40. Features in NLTK Feature Detectors
Features can be defined using feature detector functions, which map LabeledTexts to values
Method: detect, which takes a labeled text, and returns a feature value.
>>> def ball(ltext):
return (“ball” in ltext.text())
>>> fdetector = FunctionFeatureDetector(ball)
>>> document1 = "John threw the ball over the fence".split()
>>> fdetector.detect(LabeledText(document1) 1
>>> document2 = "Mary solved the equation".split()
>>> fdetector.detect(LabeledText(document2)

41. Features in NLTK
Feature Detector Lists: data structures that represent the feature detector functions for a set of features.
Feature Value Lists

42. Feature selection
How do we choose the “right” features?
Next lecture

43. Classification Define classes Label text Extract Features
Choose a classifier
>>> my_classifier.classify(token)
The Naive Bayes Classifier
NN (perceptron)
SVM
…. (next Monday)
Train it (and test it)
Use it to classify new examples

44. Training
(We’ll see what we mean exactly with training when we’ll talk about the algorithms)
Adaptation of the classifier to the data
Usually the classifier is defined by a set of parameters
Training is the procedure for finding a “good” set of parameters
Goodness is determined by an optimization criterion such as misclassification rate
Some classifiers are guaranteed to find the optimal set of parameters

45. (Linear) Classification
Linear classifier: g(x) = wx + w0
parameters: w, w0
Class2

46. (Linear) Classification
Linear classifier: g(x) = wx + w0
Changing the parameters: w, w0
Class2

47. (Linear) Classification
Linear classifier: g(x) = wx + w0
Class2
For each set of parameters: w, w0, calculate error

48. (Linear) Classification
Linear classifier: g(x) = wx + w0
Class2
For each set of parameters: w, w0, calculate error

49. (Linear) Classification
Choose the classier with the lower rate of misclassification
Class1
Linear classifier: g(x) = wx + w0
Class2
For each set of parameters: w, w0, calculate error

50. Testing, evaluation of the classifier
After choosing the parameters of the classifiers (i.e. after training it) we need to test how well it’s doing on a test set (not included in the training set)
Calculate misclassification on the test set

51. Evaluating classifiers
Contingency table for the evaluation of a binary classifier
GREEN is correct
RED is correct
GREEN was assigned a b
RED was assigned c d
Accuracy = (a+d)/(a+b+c+d)
Precision: P_GREEN = a/(a+b), P_ RED = d/(c+d)
Recall: R_GREEN = a/(a+c), R_ RED = d/(b+d)

52. Training size The more the better! (usually)
Results for text classification*
*From: Improving the Performance of Naive Bayes for Text Classification, Shen and Yang

53. Training size
*From: Improving the Performance of Naive Bayes for Text Classification, Shen and Yang

54. Training size
*From: Improving the Performance of Naive Bayes for Text Classification, Shen and Yang

55. Training Size Author identification
Authorship Attribution a Comparison Of Three Methods, Matthew Care

56. Next Time and Upcoming Define classes Label text Features (Wednesday)
Classifiers (next week)
The Naive Bayes Classifier
NN (perceptron)
SVM
Decision trees
K nearest neighbor
Maximum Entropy models