Based on the title, looks like we will be having a boring lesson...

But don't be sad too fast.
Probably when we learn along the way, you will find some interests~

The Cloud Natural Language API lets us extract entities from text, perform sentiment and syntactic analysis, and classify text into categories.

1. Open Google Cloud Platform ( follow the step in A Tour of Qwiklabs and Google Cloud )

2. Activate Cloud Shell
   Like what we did in the previous lesson.

3. Create an API Key
   Like what we did in the previous lesson.

4. Make an Entity Analysis Request
   This analyzeEntities method can extract entities (like people, places, and events) from text.

4-1. Create a request.json file and add the following code:

{
  "document":{
    "type":"PLAIN_TEXT",
    "content":"Joanne Rowling, who writes under the pen names J. K. Rowling and Robert Galbraith, is a British novelist and screenwriter who wrote the Harry Potter fantasy series."
  },
  "encodingType":"UTF8"
}

This API supports type values are PLAINTEXT or HTML.

4-2. Call analyzeEntities method:

curl "https://language.googleapis.com/v1/documents:analyzeEntities?key=${API_KEY}" \
  -s -X POST -H "Content-Type: application/json" --data-binary @request.json > result.json

The result will be something like this:

Salience -> a number in the [0,1] range that refers to the centrality of the entity to the text as a whole.

5. Sentiment analysis with the Natural Language API

5-1. Replace the content with the following code in request.json

{
  "document":{
    "type":"PLAIN_TEXT",
    "content":"Harry Potter is the best book. I think everyone should read it."
  },
  "encodingType": "UTF8"
}

5-2. Run analyzeSentiment method:

curl "https://language.googleapis.com/v1/documents:analyzeSentiment?key=${API_KEY}" \
  -s -X POST -H "Content-Type: application/json" --data-binary @request.json

The result will be like this:

• partOfSpeech -> tells you that "Joanne" is a noun.
• dependencyEdge -> includes data that you can use to create a dependency parse tree of the text.
• headTokenIndex -> the index of the token that has an arc pointing at "Joanne". Think of each token in the sentence as a word in an array.
• lemma -> the canonical form of the word. For example, the words run, runs, ran, and running all have a lemma of run. The lemma value is useful for tracking occurrences of a word in a large piece of text over time.

A dependency parse tree for the sentence above would look like this:

6. Multilingual natural language processing
   The Natural Language API also supports languages other than English.

6-1. Modify the code in request.json with a sentence in Japanese:

{
  "document":{
    "type":"PLAIN_TEXT",
    "content":"日本のグーグルのオフィスは、東京の六本木ヒルズにあります"
  }
}

Notice that you didn't tell the API which language the text is, it can automatically detect it!

6-2. Run analyzeEntities method:

curl "https://language.googleapis.com/v1/documents:analyzeEntities?key=${API_KEY}" \
  -s -X POST -H "Content-Type: application/json" --data-binary @request.json

The result is very cool:

Even cooler is the wikipedia URLs point to the Japanese Wikipedia pages!!!

What a smart text analysis!!!

Surprise! Today's lesson is over!

Didn't expect it's a short and sweet article this time right~

The natural language is so powerful!

It "speaks" our languages and even "understands" more language than we do!

Hope you enjoy today's sharing~