题目
题目

DD2380 HT24 (AIHT24_2) Q7: CV and NLP

多项选择题

Mark all of the following application examples, where n-gram models are likely to work well:

选项
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."
查看解析

查看解析

标准答案
Please login to view
思路分析
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 explanation

登录即可查看完整答案

我们收录了全球超50000道考试原题与详细解析,现在登录,立即获得答案。

类似问题

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.

更多留学生实用工具

加入我们，立即解锁 海量真题 与 独家解析，让复习快人一步！