We intend to write a regular expression to match the string “The” however our regular expression is also matching strings like “other” and “them” because they contain the set of characters “the” in them. We fixed this by building an appropriate regular expression. Now our regular expression matches only “The”. Which of the following happened as a result :

Which is a normalization step?

Assume that your corpus consists of 1000 unique characters. The Byte Pair Encoding algorithm runs on your corpus for 500 iterations creating a new merge every iteration. The algorithm outputs a vocabulary at the end of its execution. What is the size of this vocabulary i.e. how many elements are in the vocabulary ?

Which of the following is a valid bigram from the sentence "I love NLP"?

Which regex pattern would most accurately match a standard email address (e.g., "[email protected]") with least error among the given options. Assume that underscores are not present in the email?