We sometimes encounter ambiguous letters when reading handwritten words, but we can still interpret the words. For example, the same shape can be interpreted as an A in CAT but an H in THE. At what level of analysis does the feature net resolve this issue?

Question

Bram

Social Studies

22 December, 22:12

We sometimes encounter ambiguous letters when reading handwritten words, but we can still interpret the words. For example, the same shape can be interpreted as an A in CAT but an H in THE. At what level of analysis does the feature net resolve this issue?

+5

Answers (1)

Know the Answer?

Gideon Benton · Answer 1

The bigram level

Explanation:

The bigram level of analysis is an example of the N-gram model (as we can also have trigram). It is used in statistical language models to calculate probability and interprete letters in words based on previous occurrence (preceding word). In other words a bigram (less commonly called digram) makes prediction using conditional probabilities that are based on previous word. A tigram would do just same thing but predicts based on two preceding words.