UiPath UiPath Certifications UIPATH-SAIV1 Questions & Answers

• Question 1:

  For what purpose can data coming from human validation be used in AI Center?

  A. To evaluate the ML model.

  B. To retrain the ML model.

  C. To keep track of corrections done on the extracted data.

  D. To keep track of the number of documents that require human validation.

  Correct Answer: B

  Using Data Labeling with human in the loop Data Labeling enables you to upload raw data, annotate text data in the labeling tool (for classification or entity recognition), and use the labeled data to train ML models. Apart from this, you can use data labeling for human validation on model outputs.

  A common scenario is when you train an extractor or classifier model. When the model prediction falls below a set confidence threshold, that data can be sent to Action Center for human validation. The validated data can be used to retrain the model in order to improve confidence on subsequent model predictions.

  https://docs.uipath.com/ai-center/automation-cloud/latest/user-guide/using-data-labeling-with-human-in-the-loop

• Question 2:

  How does adding missed entities impact entity performance in UiPath Communications Mining?

  A. It improves precision and recall.

  B. It reduces precision and recall.

  C. It only affects recall.

  D. It has no impact on entity performance.

  Correct Answer: C

• Question 3:

  Given the following scenario: You have a trained version of the Document Understanding Model with 1000 pages called v22.10.0.1. You have an evaluation dataset of 100 pages that gave a score of 0.72 for v22.10.0.1. The business team labeled 800 pages and they ask for an increment of the Model that would contain all 1000+800 pages.

  What is the first recommended pipeline run configuration to create the new version?

  A. Run a Pipeline on the Package with the following settings: Pipeline type: Full Package Major Version: 22.10.0 Package Minor Version: 1 Input Dataset: 800 pages Evaluation Dataset: 100 pages

  B. Run a Pipeline on the Package with the following settings: Pipeline type: Training Package Major Version: 22.10.0 Package Minor Version: 1 Input Dataset: 1000+800 pages Evaluation Dataset: N/A

  C. Run a Pipeline on the Package with the following settings: Pipeline type: Full Package Major Version: 22.10.0 Package Minor Version: 0 Input Dataset: 1000+800 pages Evaluation Dataset: 100 pages

  D. Run a Pipeline on the Package with the following settings: Pipeline type: Evaluate Package Major Version: 22.10.0 Package Minor Version: 0 Input Dataset: 1000+800 pages Evaluation Dataset: 100 pages

  Correct Answer: B

• Question 4:

  What is the minimum number of pinned examples users should provide per label in UiPath Communications Mining?

  A. 5

  B. 10

  C. 15

  D. 25

  Correct Answer: D

• Question 5:

  When is ERR_AbortProcess.xaml executed?

  A. When there is an exception with a classified document.

  B. When there is an exception with a non-classified document.

  C. When a process is aborted due to a terminating exception.

  D. When an email should be sent.

  Correct Answer: C

• Question 6:

  What is the recommended data extraction methodology to be used when processing documents where data points don't have a fixed structure or position in the document layout?

  A. Rule-based data extraction.

  B. Manual data extraction.

  C. Hybrid data extraction.

  D. Model-based data extraction.

  Correct Answer: D

• Question 7:

  Which UiPath Communications Mining model performance factor assesses how well the platform predicts every concept in the taxonomy?

  A. Underperforming labels.

  B. Balance.

  C. Average label performance.

  D. Coverage.

  Correct Answer: C

• Question 8:

  What can the Semantic Similarity out-of-the-box model be used for?

  A. Understand sentiment in product reviews, customer surveys, social media posts, and emails.

  B. Relate customer questions to FAQ documents and automatically pull responses from these documents.

  C. Classify text in resumes, emails, web pages, and other formats.

  D. Extract and classify text in emails, letters, web pages, research papers, and call transcripts.

  Correct Answer: B

  Semantic Similarity

  Out of the Box Packages > UiPath Language Analysis > Semantic Similarity

  NOTE:

  The Semantic similarity model is currently in public preview.

  UiPath is committed to stability and quality of our products, but preview features are always subject to change based on feedback that we receive from our customers. Using preview features is not recommended for production deployments. This model allows you to compare a single reference sentence with bunch of other candidate sentences and ranks these candidate sentences in order of similarity https://docs.uipath.com/ai-center/automation-cloud/latest/user-guide/semantic-similarity

• Question 9:

  How are the Number of Messages calculated in UiPath Communications Mining's thread analytics?

  A. It is calculated by summing up the total number of words in all messages within a thread.

  B. It is calculated by counting the number of unique days on which messages were sent in the thread.

  C. It is calculated by counting the total number of participants in a conversation and assuming each participant sent one message.

  D. It is calculated by taking a count of the number of messages that are part of the same thread.

  Correct Answer: D

  Number of Messages

  The platform will display the threaded volume by number of messages, as well as the top label volumes by number of messages.

  The number of messages is calculated by taking a count of the number of messages that are part of the same thread.

  https://docs.uipath.com/communications-mining/automation-cloud/latest/user-guide/using-reports

• Question 10:

  Which is the most suitable extractor for extracting data from a survey?

  A. The Regex Based Extractor.

  B. The Intelligent Form Extractor.

  C. The Machine Learning Extractor.

  D. FlexiCapture Extractor.

  Correct Answer: B