Configuring the IBM Bluemix Natural Language Classifier on Question Types

1. Configuring the Classifier
on IBM Bluemix
craigtrim@gmail.com

2. QUESTION TYPE CLASSIFICATION
DATA PREPARATION ...
Part 1

3. 1. Verification: invites a yes or no answer.
2. Disjunctive: Is X, Y, or Z the case?
3. Concept completion: Who? What? When? Where?
4. Example: What is an example of X?
5. Feature specification: What are the properties of X?
6. Quantification: How much? How many?
7. Definition: What does X mean?
8. Comparison: How is X similar to Y?
9. Interpretation: What is the significance of X?
10. Causal antecedent: Why/how did X occur?
11. Causal consequence: What next? What if?
12. Goal orientation: Why did an agent do X?
13. Instrumental/procedural: How did an agent do X?
14. Enablement: What enabled X to occur?
15. Expectation: Why didn't X occur?
16. Judgmental: What do you think of X?
 Questions are often generated by
a person's knowledge deficits
and cognitive disequilibrium,
which occurs when there are
obstacles to goals,
contradictions, impasses during
problem solving, anomalous
information, and uncertainty.
Question Types

4. A total of 5 points are distributed for
each question
Questions are gathered from public
domain sources off the internet
Point distribution is manual
Classification

5. Python script to take CSV formatted
data from Excel Spreadsheet
Creates a CSV file that the NL Classifier
can understand
Classification

6. DEPLOYING TO BLUEMIX
IN 5 SIMPLE STEPS ...
Part 2

7. Step 1: Access the Service (Slide 1)
IBM Bluemix Homepage

8. Step 1: Access the Service (Slide 2)
IBM Bluemix Homepage

9. Step 1: Access the Service (Slide 3)

10. Step 1: Access the Service (Slide 4)

11. Step 1: Access the Service (Slide 5)

12. Step 1: Access the Service (Slide 6)

13. Step 2: Add the Service (Slide 1)

14. Step 3: Access the Toolkit (Slide 1)

15. Step 3: Access the Toolkit (Slide 2)

16. Step 4: Deploy to Bluemix (Slide 1)

17. Step 4: Deploy to Bluemix (Slide 2)

18. Step 4: Deploy to Bluemix (Slide 3)

19. Step 5: View the App (Slide 1)

20. Step 5: View the App (Slide 2)

21. Step 5: View the App (Slide 3)

22. Step 5: View the App (Slide 3)

23. Step 5: View the App (Slide 4)

24. Step 5: View the App (Slide 5)

25. TRAINING A CLASSIFIER
IN 5 SIMPLE STEPS ...
Part 3

26. Step 1: Train a Classifier (Slide 1)

27. Step 1: Train a Classifier (Slide 2)

28. Step 2: Prepare the Data (Slide 1)

29. Format
• The data format is:
text,class
• The text is the actual question
or user statement; some real
world example
• The class is the classification of
this real world example
– Only [A-Za-z0-9] are permitted
– Use “myClassName” rather than
“my_class_name”
• The text and the class are
comma separated, with the
text occurring first
Example
what is the difference between being
alive and truly living?,comparison
"when is it time to stop calculating
risk and rewards and just go ahead
and do what you know is
right?”,conceptCompletion
"when is it time to stop calculating
risk and rewards and just go ahead
and do what you know is
right?”,interpretation
"if we learn from our mistakes why
are we always so afraid to make a
mistake?”,enablement
Step 2: Prepare the
Data (Slide 2)

30. Step 3: Import the Data (Slide 1)

31. Step 4: Train the Classifier (Slide 1)

32. Step 4: Train the Classifier (Slide 2)

33. Step 4: Train the Classifier (Slide 3)

34. Step 5: Use the Classifier (Slide 1)

35. Step 5: Use the Classifier (Slide 3)

36. Step 5: Use the Classifier (Slide 4)

37. Step 5: Use the Classifier (Slide 4)

38. Step 5: Use the Classifier (Slide 4)

39. ACCESSIBILITY
ACCESS AND GET/POST
Part 4

40. Optional: Rename the Service (Slide 1)

41. Optional: Add another Route (Slide 1)

42. Optional: Add another Route (Slide 2)

43. @RequestMapping(
value="/classify",
params="text",
method=RequestMethod.GET,
produces=MediaType.APPLICATION_JSON_VALUE)
@ResponseBody
public String classify(
@RequestParam("text") String text) {
NaturalLanguageClassifier classifierService = new NaturalLanguageClassifier();
classifierService.setUsernameAndPassword(username, password);
Classification classification = classifierService.classify(route, text);
ObjectMapper mapper = new ObjectMapper();
try{
return mapper.writerWithDefaultPrettyPrinter().
writeValueAsString(classification);
} catch(JsonProcessingException e){
logger.error(e);
}
}
Optional: Java Code
(Slide 1)
<dependency>
<groupId>com.ibm.watson.developer_cloud</groupId>
<artifactId>java-wrapper</artifactId>
<version>1.1.0</version>
</dependency>