UiPath UiPath Certifications UIPATH-SAIV1 Questions & Answers

• Question 91:

  What is the correct approach when discovering that a label's name does not reflect the desired intent within a UiPath Communications Mining taxonomy?

  A. Export dashboards where the original label appeared, then manually change the name.

  B. Create another label with the correct name and apply it to all verbatims that have the original label.

  C. Create a label intending to show the error in naming and insert it into all dashboards where the original label appeared.

  D. Rename the label in the taxonomy as it doesn't negatively affect the model training and performance.

  Correct Answer: D

• Question 92:

  What is the correct way to start a Document Understanding job in Unattended scenarios?

  A. Having the Dispatcher process use a Start Job and Get Reference activity.

  B. Starting a batch job that runs the Document Understanding Process for all the needed documents.

  C. Starting the job from Orchestrator from the Processes tab.

  D. Using a Time Trigger that runs every 5 minutes.

  Correct Answer: C

• Question 93:

  What is the order of magnitude when looking at UiPath Communications Mining objects?

  A. Message < Source < Dataset < Project

  B. Source < Message < Project < Dataset

  C. Message < Dataset < Source < Project

  D. Source < Dataset < Message < Project

  Correct Answer: C

• Question 94:

  When adding a new label to a mature taxonomy in UiPath Communications Mining, why is it important to apply it to all of the relevant examples in the previously reviewed set?

  A. Training data for each label should always be evenly spread across the time period covered in the dataset.

  B. If the new label is not applied to relevant previously reviewed verbatims, the model will start predicting other labels less accurately.

  C. It will reduce bias for the new label.

  D. The previously reviewed examples where the new label should also have been applied will cause confusion for the model if not corrected.

  Correct Answer: D

• Question 95:

  What does the Export stage of the Document Understanding Framework do?

  A. Converts the result of extraction to a dataset or to a customized format.

  B. Allows a human to validate and correct the extracted data.

  C. Classifies the document as one of the predefined document types.

  D. Extracts the text out of the image document using OCR (Optical Character Recognition).

  Correct Answer: A

• Question 96:

  How can you build custom models supported by AI Center?

  A. Using the AI Center IDE (Integrated Development Environment).

  B. Using the AI Center model builder.

  C. Using a Python IDE (Integrated Development Environment) or an AutoML platform.

  D. Using a C/C++ IDE (Integrated Development Environment), then upload the code to Al Center IDE.

  Correct Answer: C

  Building ML Packages

  The data scientists build pre-trained, models using Python or using an AutoML platform. Those models are consumed by RPA developers within a workflow.

• Question 97:

  What is the recommended split of documents for training and evaluation, considering a total of 15 documents per vendor?

  A. 7 documents for training the model, and 8 for evaluating the model.

  B. 8 documents for training the model, and 7 for evaluating the model.

  C. 10 documents for training the model, and 5 for evaluating the model.

  D. 12 documents for training the model, and 3 for evaluating the model.

  Correct Answer: C

• Question 98:

  How is the Taxonomy component used in the Document Understanding Template?

  A. To define the document types and the pieces of information targeted for data extraction (fields) for each document type.

  B. To apply rigor in the taxonomy of data, ensuring any newly discovered object fits into one and only one category or object.

  C. To organize knowledge by using a controlled vocabulary to make it easier to find related information.

  D. To apply relationship schemas other than parent-child hierarchies, such as network structures on the processed data.

  Correct Answer: A

  The Taxonomy is the metadata that the Document Understanding framework considers in each of its steps. A Taxonomy is a collection of Document Types. A Document Type is the definition of a logical type of document, that must be handled by different business processes.

• Question 99:

  How can the code be tested in a development or testing environment in the context of the Document Understanding Process?

  A. Use them as a template to create other tests.

  B. Simply run the existing tests.

  C. Based on the use case developed, create test data to test existing and new tests.

  D. Based on the use case developed, create test data to test existing tests.

  Correct Answer: C

• Question 100:

  What information does the comparison between two cohorts display on the Comparison page in UiPath Communications Mining?

  A. Total verbatim count and proportion for each label.

  B. Entity count for each metadata.

  C. Verbatim content for each label.

  D. Differences in verbatim length between Group A and Group B.

  Correct Answer: A