UiPath UiPath Certifications UIPATH-SAIV1 Questions & Answers

• Question 111:

  What are the out-of-the-box model types available in AI Center?

  A. Pre-trained, custom training, and reviewed.

  B. Custom training, fine-tunable, and reviewed.

  C. Pre-trained, fine-tunable, and reviewed.

  D. Pre-trained, custom training, and fine-tunable.

  Correct Answer: D

• Question 112:

  What is the Machine Learning Extractor?

  A. A specialized model that can recognize multiple languages in the same document using API calls to a Hugging Face model with over 250 languages.

  B. An extraction model that can be enabled and trained in AI Center. For better accuracy, 25 documents per model are recommended to train the model.

  C. A tool using machine learning models to identify and report on data targeted for data extraction.

  D. A tool that helps extract data from different document structures, and is particularly useful when the same document has multiple formats.

  Correct Answer: D

• Question 113:

  Which of the following is an indicator that sufficient training has been completed for a model in UiPath Communications Mining?

  A. A model rating of 30-40.

  B. A model rating of 40-50.

  C. A model rating of 50-60.

  D. A model rating of 70-90 or better.

  Correct Answer: D

• Question 114:

  What is one best practice when designing a UiPath Communications Mining label taxonomy?

  A. Each label should be identifiable from the text of the individual verbatim (not thread) to which it will be applied.

  B. Each label should include customer experience/sentiment analysis in its coverage.

  C. Each parent label should have at least 3 children labels to ensure specificity.

  D. Each label should overlap slightly with a few distinct others so we ensure 100% coverage.

  Correct Answer: A

• Question 115:

  What is the recommended number of documents per vendor to train the initial dataset?

  A. 5

  B. 10

  C. 15

  D. 20

  Correct Answer: B

• Question 116:

  What can be done in the Reports section of the dataset navigation bar in UiPath Communication Mining?

  A. Train models using unsupervised learning.

  B. View, save, and modify dataset model versions.

  C. Monitor model performance and receive recommendations.

  D. Access detailed, queryable charts, statistics, and customizable dashboards.

  Correct Answer: D

• Question 117:

  What is the difference between OCR (Optical Character Recognition) and IntelligentOCR?

  A. OCR (Optical Character Recognition) is a method that reads text from images, recognizing each character and its position, while IntelligentOCR is an enhanced version of it that can also work with noisier input data.

  B. IntelligentOCR is simply a rebranding of the OCR (Optical Character Recognition), both of them being methods that read text from images, recognizing each character and its position.

  C. OCR (Optical Character Recognition) is a UiPath Studio activity package that contains IntelligentOCR as an activity used to read text from images, recognizing each character and its position. OCR is widely used in Document Understanding processes.

  D. IntelligentOCR is a UiPath Studio activity package that contains all the activities needed to enable information extraction, while OCR (Optical Character Recognition) is a method that reads text from images, recognizing each character and its position.

  Correct Answer: D

• Question 118:

  Which UiPath Communications Mining model performance factor assesses the proportion of the entire dataset that has informative label predictions?

  A. Average label performance.

  B. Coverage.

  C. Balance.

  D. Underperforming labels.

  Correct Answer: B

  Coverage is a term frequently used in Machine Learning and relates to how well a model 'covers' the data it's used to analyse. In Communications Mining, this relates to the proportion of messages in the dataset that have informative label predictions, and is presented in Validation as a percentage score.

  'Informative labels' are those labels that the platform understands to be useful as standalone labels, by looking at how frequently they're assigned with other labels. Labels that are always assigned with another label, e.g. parent labels that are never assigned on their own or 'Urgent' if it's always assigned with another label, are down-weighted when the score is calculated.

  The visual below gives an indication of what low coverage versus high coverage would look like across an entire dataset. Imagine the shaded circles are messages that have informative label predictions.

• Question 119:

  Which is the correct description of the Configure Extractors Wizard?

  A. A mandatory step in the extractor configuration that allows choosing which extractors are applied to each field.

  B. A mandatory step in the extractor configuration that allows choosing which extractors are applied to each document type and field.

  C. A mandatory step in the extractor configuration that allows choosing which extractors are applied to each document type.

  D. An optional step in the extractor configuration which allows choosing which extractors are applied to each document type.

  Correct Answer: B

• Question 120:

  What is the definition of a UiPath Communications Mining data source?

  A. A collection of raw unlabeled communications data of a similar type, that can be associated with up to 10 datasets.

  B. The model that we create when training the platform to understand the data in those sources.

  C. A permissioned storage area within the platform which contains communications and labels.

  D. A user-permissioned project containing a taxonomy with labels and entities.

  Correct Answer: A

  A 'source' refers to a raw collection of messages which can grow over time. For example, a source could be all the responses collected to a survey, the emails in a team mailbox, the transcripts in a messaging channel, or all of the calls against a telephone number.

  Sources are added to datasets in order to build a model to interpret and structure the messages within them.

  Each source can be added to up to 10 different datasets.