What are examples of the information the IBM Watson Natural Language Understanding service extract from html, or web-based content when it analyzes entities?

A. text and title information

B. people, companies, organizations

C. subject-action-object relations

D. topic keywords

What output data type by the IBM Watson Natural Language Understanding service?

A. DOCX

B. PDF

C. HTML

D. JSON

What license is the IBM Watson SDK licensed under?

A. BSD License

B. Apache 2.0 License

C. GNU General Public License

D. IBM Public License

There are two security models for HTTP communications between an IBM Watson service and the client application. Which two statements are true regarding these two models? (Choose two.)

A. Both models offer generally equivalent communication latency characteristics

B. Neither model provides for direct communication between the application and the service

C. Both models use HTTP basic authentication in all communications interactions

D. Both models offer generally equivalent functionality, but with different security and performance characteristics

E. The application must manage a security token in one model but not in the other

How can the threshold for the confidence level be set for the intent of a dialog node in the IBM Watson Assistant service?

A. The confidence level cannot be set within the Dialog and should be done programmatically within the application code.

B. On the drop-down of the Dialog node, the condition for confidence levels can be set for the intents defined in your Dialog node.

C. The confidence level threshold is already set for each Dialog node at "0.2". It can be overridden by turning off the confidence level on the improve tab within the Watson Assistant workspace.

D. It can be a condition within the Dialog node alongside the intent. For Example, intents [0].confidence<0.8

When is it appropriate to include multiple classes for a sample text in the training data for IBM Watson Natural Language Classifier?

A. When the text is very detailed such that identifying a single class may cause inaccuracies.

B. When the classifier has been retained and we want to preserve old classes from a previous training set.

C. When experts interpret the same text in different ways, multiple classes support those interpretations.

D. When the text utterances are very similar in nature and we want to mark slight differences using classes.

An AI solution is implemented to detect what the user wants to do. The user mentions that wants to buy a ski jacket for an upcoming vacation in Colorado.

What design pattern is appropriate for this use case?

A. Speech to Speech pattern designed with: Speech to Text, Relationship Extraction and Text to Speech

B. Audio Analysis pattern designed with: Speech to Text and Tone Analysis

C. Empathy Analysis pattern designed with: Personality Insights and Watson Assistant

D. Conversational pattern designed with: Watson Assistant service, Natural Language Understanding and Entity Extraction

When running an application on IBM Cloud that uses the IBM Watson assistant service, what is the prerequisite to use the service?

A. That the Watson Assistant service credentials username and password are provisioned and referenced for the application.

B. That the Watson Assistant service is associated with an IBM Watson speech to Text service.

C. That the Watson Assistant service uses robust conversation collected from actual user questions.

D. That the Watson Assistant service is bound to the application.

What is the main criteria for separating training and test data when training a machine learning system?

A. Test data should be as random as possible, so that it tests the boundaries of the system.

B. Training data should be random, but the test data should be created by a subject matter expert.

C. Training data should be as random as possible, in order to create a robust model.

D. The data set should be representative and randomly split in to a training set and a test set so that they do not overlap.

What is the formula for precision in a classification system?

A. True Negatives / (True Positives + False Positives)

B. True Positives / (True Positives + False Positives)

C. False Positives / (True Negatives + False Positives)

D. True Positives / (True Positives + False Negatives)