Quick lab #1

[seabroadlab]

퀵랩 세션 1 기록

1. quick lab 계정 등록

2. quick lab 활성화

   • 가나다

   • ㄱㄱㄱ

[seabroadlab]

Cloud Natural Language API: Qwik Start

1. text documents, news articles, or blog posts 에서 멘션된 정보들을 추출
2. Syntax Analysis 등등이 가능함, 이 과제에서는 analyze-entities 를 이용 ask the Cloud Natural Language API to extract "entities" (e.g. people, places, and events) from a snippet of text.
3. 콘솔 켜기
4. gcloud is the command-line tool for Google Cloud Platform. It comes pre-installed on Cloud Shell and supports tab-completion.
5. create API key
6. use the function with syntaxes

[seabroadlab]

Speech to Text Transcription with the Cloud Speech API

1. The goal of this lecture:

   • Creating a Speech API request and calling the API with curl
   • Calling the Speech API with audio files in different languages

2. What does the curl do? Speech API에게 request를 보내게 하는것

3. To use curl: generate an API key to pass in my request URL

[seabroadlab]

Entity and Sentiment Analysis with the Natural Language API

1. analyzeEntities. With this method, the API can extract entities (like people, places, and events) from text.
2. 즉, 자연어에서 entity랑 sentiment읽는 법을 배우겠음
3. 먼저 request.json에 우리가 분석할 내용이랑, 형식 저장

• 첫째는 sentiment, analyzeEntities
  1. build your request to the Natural Language API in a request.json file. You can use your preferred command line editor (nano, vim, or emacs)= vi request.json 이런식으로 실행하면 request.json이라는 파일이 생성. 이제 이안의 파일내용을 vim으로 편집하는것(i는 insert모드 1.vi 잘못쳐서 나가고싶을땐 esc 연타후 :q!, q나감, wq저장후나가기, :wq
  2. vi request.json 들어가서 기존내용 replace하고싶을떄: insert mode에서 백스페이스
  3. 그 다음 gcloud로 돌아와서 curl이용해 url과 api키 제공하고 분석 시키기

1. sentiment analysis 결과물로 나오는것은(분석 전체 자연어 blocks단위도 가능, 문장별로도 가능)
   1. score - is a number from -1.0 to 1.0 indicating how positive or negative the statement is.
   2. magnitude - is a number ranging from 0 to infinity that represents the weight of sentiment expressed in the statement, regardless of being positive or negative.

• 다음으로는 Entity 분석, analyzeEntitySentiment

  1. 동일 vi request.json
  2. 그결과 entity name과 type, sentiment분석 후 -magnitude, score 출력+ 각 문장별 분석도 같이
  3. You also may notice that there are two sentiment objects returned for each entity. If either of these terms were mentioned more than once, the API would return a different sentiment score and magnitude for each mention, along with an aggregate sentiment for the entity.

• 마지막 annotateText

  1. 역할 an advanced method that provides a full set of details on the semantic and syntactic elements of the text. For each word in the text, the API will tell us the word's part of speech (noun, verb, adjective, etc.) and how it relates to other words in the sentence (Is it the root verb? A modifier?)

1.결과로 나오는 것들 partOfSpeech tells us that "Joanne" is a noun. dependencyEdge includes data that you can use to create a dependency parse tree of the text. Essentially, this is a diagram showing how words in a sentence relate to each other. A dependency parse tree for the sentence above would look like this: