I hinted at this in some of the lecture material.

Let's go back and see why.

lest we confuse whitespace and the body of strings.

This looks very good.

Misspelled Words

What we want to do is chop up those strings into substrings.

Web browsers use the same sort of techniques we talked about in the last unit to break up sentences like these into words based on white space.

... the misspelled word shown in context...

Here we have pretty much the same thing except that we appear to be returning a space as a word.

Let me draw that a little bit neater.

We just want to maximize the probability of each individual word regardless of the word that comes before or after it.

Down here we have almost the same sentence, but there's no space between salvador and dali.

Here grace is a word, some white space, hopper is a word, some white space, 1 is a number, but because there's white space between the 1 and the 9, this is going to register as 4 different numbers instead of just one, so it doesn't match this specification exactly.

But I'm not just going to remove it.

We're friends from Space Camp.

Lookup words

Continue

Unknown word

Unknown word

This sometimes causes problems, and this is why many languages don't pay any attention to white space.

Whole words

As a noun, it means uncertainty or confusion.

Let's see if we can go farther.

Is will match the word is.

We'll get out a list where each element of the list corresponds to one of the words in this string separated by spaces.

Suppose our word rule comes first, just like it does here on the page in some sense.

Words

15, entry 1.

Page 15, entry 1...

Page 15, entry 1.

Thoughtfulness is a long word in English.

Aha! Today's word is..

Here, let's say this is the E in elegant misspelled as an A.

Well, unlike the previous example, this is a little bit harder to see.

But to learn from this text, what we really want to discover is what individual words in Chinese correspond to individual words or small phrases in English.

Antonyms Words with Opposite Meanings

How many English words do you know?

Like this? Cheska is a great actress Cao Lu

Turn to page 15 and it's the first word you read.

That's one of the reasons why making this naive Bayes assumption is so helpful.

And it's the same with the brain.

So, please take a second, and... take ten seconds, and look at these two sets of words.

TeX Word

Words

Words