Practice Exam Q&A

In Watson Assistant, entities represent what the user wants to achieve: a goal, an action, or verbs.

False

The IBM Language Translator service cannot be trained for new domains and languages.

False

In Watson Assistant, dialog node conditions can evaluate intents and entities only.

False (page 510)

Which three factors drove the emergence of Deep Learning? (Choose 3) A. Advancement in algorithms like the rectified linear unit (ReLU) B. Improvement in processing power and the usage of GPUs to train neural networks. C. Emergence of big data, which requires data processing scaling. D. The Emergence of cloud platform benefits and capabilities, such as availability, scalability, and rapid deployment

A, B, C

Which are IBM Watson's capabilities? (Choose 3) A. Interacts naturally with people. B. Learns and reasons at scale C. Performs ETL and data migration jobs. D. Understands all forms of data.

A, B, D (page 106)

You performed feature extraction on an image and ended up with a huge set of features, where some are redundant and irrelevant. What is the best course of action? (Choose 1) A. Perform Pre-processing on the image B. Start Visual Recognition Model Training C. Perform Feature Selection on the available features D. Perform Segmentation on the image

C

What are examples of augmented reality (AR)? (Choose 2) A. Learning how to land a plane by using simulated landing scenarios B. Being immersed in a fictional world by using Oculus goggles C. Attaching bunny ears to your own head in a Snapchat image D. Playing Pokémon go

C, D

What are the core functions of a chatbot? (Choose 3) A. Translation B. Computer Vision C. Intent Classification D. Dialog maintainability E. Entities identification

C, D, E

Porter is the most popular English stemming algorithm.

True

Relation identification is an example of what? (Choose 1) A. Information extraction B. Sentiment analysis C. Natural language classification D. Conversation systems

A [Entity extraction, relation identification extraction, text summarization - Unit 5]

What are the basic goals of conversational interaction for chatbots? (Choose 3) A. Decrease sympathy and forgiveness in users B. Extract insights about the users C. Manage user expectations D. Help achieve the purpose of the solution and drive value

B, C, D

Which of the following items are types of output that are expected from the NLU service? (Choose 2) A. Paragraph summary B. Entities C. Intents D. Sentiment analysis

B, D

Which of the following items are Watson Studio offerings? (choose 3) A. Watson Studio Analytical B. Watson Studio Desktop C. Watson Studio Automation D. Watson Studio Cloud E. Watson Studio Local

B, D, E

In Watson Assistant, which of the following items are System Entities? (Choose 3) A. @sys-email B. @sys-date C. @sys-currency D. @email pattern entity: \b[a-zA-Z0-9.!#$%&'*+/=?^_`{|}~-]+@[A-Z0-9.-]+\.[A-Z]{2,}\b E. @sys-number

B, D, E (90%) ?????

Which are the typical use cases of integrating Watson Assistant with Watson Natural Language Understanding? (Choose 2) A. Converting Text to Speech B. Translating the user input text to another language C. Detecting the date and time in the user input D. Detecting a location in the user input

C, D

Which is NOT an example of an asset that can be added to a Watson Studio project? (choose 1) A. Trained Models B. Experiments C. Database connected from an external source D. Notebook added from Watson Studio Gallery E. Collaborators

E

In the Data Preparation phase, data preprocessing activities consider what data is available, what data is missing, and what data can be removed.

False [Data Selection - Unit4]

To enable Watson Assistant integration, an intent is an object that is used to maintain the state information, and it must be passed back and forth between the application and the Watson Assistant service.

False (Context)

A project Editor can add another team member as a viewer in Watson studio project.

False (Only admin can add members)

Markdown cells in Jupyter Notebook allow Data Scientists to run Python or R codes and see the resulting visualizations (like pie charts).

False [Run cell]

Pseudo-labeling is an example for a technique that is used in semi-supervised learning.

True (page 32)

In Watson Assistant, dialog can respond with a pause then a text response.

True (page 509)

Which of the following statements are correct regarding the definition of Homophones and Homographs? (Choose 2) A. Homographs are words that have the same written form but have unrelated meanings. B. Homophones are words that have similar sound when spoken but have different meanings or spellings. C. Homophones are words that have the same written form but have unrelated meanings. D. Homographs are words that have similar sound when spoken but have different meanings.

A, B

Which of the following items is NOT a data challenge that requires preprocessing techniques? (Choose 1) A. Missing values B. Data description C. Noise and outliers D. Inconsistent values E. Duplicate data

B

You can provide the data to train the Natural Language Classifier in comma-separated value (CSV) format in which a row represents an example record. A record should contain at least how many columns? (choose 1) A - 1 B - 2 C - 3 D - 4

B (الفيتشر والتارجت )

From a high-level perspective, which of the following items are NLP categories? (choose 2) A. Natural Language Identification (NLI) B. Natural Language Understanding (NLU) C. Natural Language Generation (NLG) D. Natural Language Creation (NLC)

B, C

A spam classifier is a system that looks at the content of the email subject line to assess whether the received email is or is not spam. The system is trained with a labeled training set that contains enough samples of spam and legitimate emails. This method of training is common in which machine learning approach? (Choose 1) A. Classification for Unsupervised learning B. Linear regression for Supervised learning C. Classification for Supervised learning D. Linear regression for Unsupervised learning

C

Generally, what are the first two operations in an NLP pipeline? (Chosse 1) A. Sentence-level semantics and Part of speech (POS) tagging B. Part of speech (POS) tagging and Morphological processing C. Sentence segmentation and Tokenization D. Word-level (lexical) semantics and Parsing (syntax)

C

Here is an example of a chatbot: Customer: What is the status of my shipment no 123456789? Chatbot: Your shipment is out for delivery. Which type of chatbot does this conversation represent? (Choose 1) A. Viewpoint B. Reactive C. Proactive

C

In Watson Assistant integration, which Watson service can be used in the post-processing layer? (Choose 1) A. Speech to Text B. Watson Knowledge Studio C. Watson Discovery D. Watson Assistant

C

In Watson Knowledge Studio, what groups words and phrases that should be treated equivalently by a model? (Choose 1) A. Type system B. Regular expressions C. Dictionaries D. Documents

C

What are words that share a form, but have unrelated meanings called? (Choose 1) A. Polysemes B. Antonyms C. Homonyms D. Synonyms

C

What does CRISP-DM stand for? (Choose 1) A. Common-Recipes Including Standard Process for Data Modeling B. Cross-Industry Standard Process for Data Modeling C. Cross-Industry Standard Process for Data Mining D. Common-Recipes Including Standard Process for Data Mining

C

What does feature selection in a computer vision pipeline NOT help with? (Choose 1) A. Reducing the features dimensionality B. Creating simpler models with less training time C. Resizing the image as a form of normalization D. Avoiding overfitting when training the model with the features That's rIght!

C

What is a process to evaluate a model by dividing the data set once or several times in training and testing called? (Choose 1) A. A/B testing B. Leave one out cross validation (LOO-CV): C. Cross-validation (CV) D. K-fold cross validation

C

What is the most time-consuming phase in CRISP-DM? (Choose 1) A. Data understanding B. Model design, implementation, and deployment C. Data preparation D. Model testing and validation

C

Which component is optional when developing a question and answer (FAQs) chatbot? (Choose 1) A. Intent Classification B. Chatbot UI C. Dialog construction D. Entities identification

C

Which service can be integrated with Watson Assistant to retrieve a response from FAQ documents? (Choose 1) A. Natural Language Classifier B. Natural Language Understanding C. Watson Discovery D. Watson Knowledge Catalog

C

Which of the following statements are correct regarding the definition of Hyponymy and Polysemy? (Choose 2) A word is a polysem of another word if it represents a subclass of the other word. B. Hyponymy is words that have the same written form and related meaning. C. Polysemy is words that have the same written form and related meaning. D. A word is a hyponym of another word if it represents a subclass of the other word.

C, D

In chatbot design, what is defining the chatbot's job description known as? (Choose 1) A. Viewpoint B. Proactivity C. Purpose D. Tone

C??

Chatbots cannot be both Reactive and Proactive at the same time.

False

If an image is represented in gray scale, the pixel intensity 0 represents white, while 255 represents black.

False

In an image that follows the RGB color model, a pixel is represented by ONLY one color, either Red, Green or Blue.

False

The ONLY way to deploy a model by using Watson Machine Learning is through a Jupyter Notebook.

False

You are testing a document retrieval algorithm for a search engine, you entered a certain search word and it retrieved some documents. True Negative represents irrelevant documents that were retrieved by the algorithm.

False

Using tags and keywords to retrieve images from a database is considered Content-Based Image Retrieval.

False (Content-based image retrieval is preferred because searches that rely purely on metadata depend on the quality of annotation.) (Other image retrieval systems rely on image metadata such as keywords, tags, or descriptions that are associated with the image instead of image content)

IBM Watson Natural Language Classifier can be used to forecast the next three days' weather based on its historical records.

False (NLG page 290)

Watson Knowledge Studio can create machine learning models that can be used in Watson Natural Language Classifier.

False (NLU not NLC) مش متاكده من الي بين القوسين

Non-response survey bias occurs when some members of the population are inadequately represented in the sample.

False (Under-converage page 216)

Jupyter Notebooks and Zeppelin Notebooks are both available in the Watson Studio Cloud offering.

False [ Watson Studio Local only]

Scaling, aggregation, and decomposition are some of the most common data transformation activities.

True

The Watson Discovery News collection is continuously updated automatically.

True

With Watson Knowledge Studio we no longer need human annotators.

True

In chatbot design, what is the degree to which the chatbot engages and guides the user known as? (Choose 1) A. Proactivity B. Tone C. Purpose D. Viewpoint

A

Lexical ambiguity occurs on a what level? (Choose 1) A. Word B. Document C. Paragraph D. Sentence

A

What type of input is expected for Watson Discovery service? (Choose 1) A. Documents B. URLs C. No input is required D. Input text

A

_________ is a service on IBM Cloud with features for training, deploying, and scoring machine learning models and neural networks. It is also integrated with IBM Watson Studio. (Choose 1) A. Watson Machine Learning B. Watson Assistant C. Watson Neural Networks D. Watson Knowledge Studio

A

In Watson Assistant, which of the following items contains prebuilt common intents to be added to a dialog skill? (Choose 1) A. Content Catalog B. Common Intents C. Content Intents D. Intents Catalog

A (Page 496)

In Watson Assistant, how is the standard dialog flow processed? (Choose 1) A. Top to bottom, left to right. B. Both top to bottom, left to right and Bottom up, right to left. C. None of the above. D. Bottom up, right to left.

A (Page 512)

DeepQA is the name for the question-answering (QA) system architecture, which was developed for Watson to play the Jeopardy! game.Which of the following statements describe how Watson understood the text that was ingested? (Choose 2) A. DeepQA generates and scores many hypotheses by using an extensible collection of natural language processing, machine learning, and reasoning algorithms and determine the answer with the best confidence. B. Watson accessed to 200 million pages of structured and unstructured content that filled 4 TB of disk storage, including the full text of Wikipedia. C. Watson listened to humans having conversations over many hours of training. D. Watson relied on the Encyclopedia Britannica to know what each of the words mean.

A, B (page 107)

In Watson Assistant integration, which Watson services can be used in the pre-processing layer? (Choose 4) A. Natural Language Understanding B. Tone Analyzer C. Watson Assistant D. Speech to Text E. Watson Discovery

A, B, C, D

Which objects are included in the response data that is returned from the Watson Assistant message API? (Choose 5) A. output B. intents C. assistants D. entities E. skills F. context

A, B, D, F

Which of the following items are types of output that are expected from the NLU service? (Choose 2) A. Sentiment analysis B. Intents C. Entities D. Paragraph summary

A, C [Entities and relationships, Sentiment analysis, Keywords - Unit 8]

In chatbot design, which aspects are covered by positioning? (choose 2) A. Proactivity B. Tone C. Personality D. Purpose E. Agility

A, D (ViewPoint is the third one)

OCR is used for converting _______ into ______. (Choose 1) A. scanned text photos, speech format B. scanned text photos, digital text format C. speech format, text photos format D. digital text format, text photos format

B

What is the process of converting "ordinarily" to "ordinary" and "ly" an example of? (Choose 1) A. Part of speech tagging B. Morphological parsing C. Tokenization D. Stemming

B

In Information retrieval, which represents irrelevant documents the algorithm did NOT retrieve? (choose 1) A. True Positive B. True Negative C. False Negative D. False Positive

B

Information extraction is the process of changing _______ in passages, to a/n _________ format. (Choose 1) A. structured text, unstructured B. unstructured text, structured C. semi-structured text, structured

B

Clever and Smart are examples of_______, while Clever and Stupid are examples of _______? (Choose 1) A. Synonym, Hyponymy B. Antonym, Polysemy C. Antonym, Synonym D. Synonym, Antonym

D

In unsupervised learning, what is discovering the inherent groupings in data? (Choose 1) A. Association B. PCA C. Regression D. Clustering

D

Sentiment Analysis is the process of identifying what? (Choose 1) A. Personality B. Entities C. Relations D. Opinions

D

What is a data set of hand-written digits that act as a benchmark for training and testing algorithms for computer vision? (Choose 1) A. Iris B. Enron Email C. SpaceNet D. MNIST

D

What is a training set in Watson Knowledge Studio? (choose 1) A. A set of documents that were annotated to validate the model. B. A set of annotated documents that are set aside and used to evaluate the system periodically. C. A set of annotated documents that are used to test the trained model. D. A set of documents that were annotated to train the model.

D

Which step in data preprocessing is represented by the activity of gathering data from multiple sources for processing, such as multiple databases, data sources, or files? (Choose 1) A. Data Formatting B. Data Integration C. Data Sampling D. Data Dimensionality Reduction E. Data Cleaning

D

__________ is more popular with problems like image processing, while ___________ is more popular with problems like speech recognition. (Choose 1) A. CNN, MLP B. MLP, RNN C. RNN, MLP D. CNN, RNN

D

What is one of the most popular lexical databases for English Language? (Choose 1) A. NLTK B. LexNLP C. OpenNLP D. WordNet

D (Page 275)