Questions
DD2380 HT24 (AIHT24_2) Q7: CV and NLP
Multiple choice
Mark all of the following application examples, where n-gram models are likely to work well:
Options
A.Recognizing that there is a typo that was not revealed by a spell-checker, for instance in "Switch it of."
B.Suggesting the next word to come, for instance suggesting that the next word after "Thank" should be "you".
C.Choosing the right translation from one language to another, for instance translating "Jag väger ett ton." as "I weigh a ton." rather than "I weigh a tune."
View Explanation
Verified Answer
Please login to view
Step-by-Step Analysis
When evaluating where n-gram models are likely to perform well, it helps to consider what these models excel at and what tasks they are well-suited to support.
Option 1: 'Recognizing that there is a typo that was not revealed by a spell-checker, for instance in "Switch it of."' An n-gram language model can be sensitive to unnatural or improbable word sequences. In the phrase "Switch it ......Login to view full explanationLog in for full answers
We've collected over 50,000 authentic exam questions and detailed explanations from around the globe. Log in now and get instant access to the answers!
Similar Questions
What is the primary goal of language modeling?
What is a significant limitation of early N-gram language models?
Why does ChatGPT sometimes choose lower-ranked words instead of always selecting the word with the highest probability?
Fill in the blank. What does this definition refer to? ________________________________ is any system designed to assign probability to some aspect of language. How likely is it that a letter, or a word, or a phrase, will occur in a larger body of text, often called the corpus.
More Practical Tools for Students Powered by AI Study Helper
Making Your Study Simpler
Join us and instantly unlock extensive past papers & exclusive solutions to get a head start on your studies!