Text And EmbeddedVectorization — Learn free

Self-check

Questions 1–10 of 10

1. What is the primary aim of general vectorisation?
Question 1A. To convert text into imagesB. To encrypt data elements before storageC. To convert a single action on a single data element (SISD) into a single action on multiple data elementsD. To translate documents between languagesE. To compress data so it takes less disk space
2. In machine learning, what does text vectorisation specifically deal with?
Question 2A. Converting textual or character data into numerical representationsB. Converting numbers back into readable sentencesC. Removing all punctuation from a documentD. Translating text from one language to anotherE. Storing documents in a relational database
3. What happens in the embedding process after text has been converted into numbers?
Question 3A. The numbers are printed as a reportB. The numbers are deleted to save spaceC. The numbers are converted back into the original textD. Machine learning and deep learning techniques learn from the numerical representations to produce faster and more effective resultsE. The numbers are sorted alphabetically
4. Which text vectorisation method represents only whether a term appears in a document, without considering its frequency?
Question 4A. Bag of Words Term FrequencyB. Normalised Term FrequencyC. Binary Term FrequencyD. Inverse Document FrequencyE. Word embedding
5. What does Bag of Words (BoW) Term Frequency represent?
Question 5A. The order in which words appear in a sentenceB. The frequency of each term in a document, disregarding the order of wordsC. The grammatical role of each wordD. The length of each document in charactersE. Whether a document is in English
6. What adjustment does Normalised Term Frequency make?
Question 6A. It removes all rare words from the documentB. It converts all words to upper caseC. It sorts terms by alphabetical orderD. It translates terms into a common languageE. It adjusts term frequency based on document length to give a more balanced representation
7. What overarching goal do general vectorisation and text vectorisation share?
Question 7A. Accelerating tasksB. Reducing storage costsC. Improving data privacyD. Replacing databasesE. Generating images from text
8. How does general vectorisation improve efficiency?
Question 8A. By converting words to numbers for model trainingB. By removing duplicate records from a tableC. By transforming data so that multiple data elements can be processed in parallelD. By caching query results in memoryE. By compressing text into a smaller alphabet
9. Which of the following is NOT listed as a common text vectorisation method?
Question 9A. Binary Term FrequencyB. Bag of Words Term FrequencyC. Normalised Term FrequencyD. Slowly Changing Dimension FrequencyE. All of these are listed methods
10. What is the subsequent embedding step used for once text has been vectorised?
Question 10A. Formatting the text for printingB. Training machine learning models and enhancing natural language processing tasksC. Backing up the original documentsD. Checking the spelling of the original textE. Converting the numbers into a PDF