Translate text by using adaptive translation

When you request an adaptive translation, you provide the text to translate and example translations that Cloud Translation uses to tailor its responses.

For programmatic translation requests, you can include example translations in a dataset or as part of your translation request. When you use a dataset, Cloud Translation automatically selects five reference sentences that are most similar to your source sentence to customize translations. If you include reference sentences in your translation request, Cloud Translation uses all of them to customize the translation.

Before you begin

To use adaptive translation, you must enable the Cloud Translation API in your project and set up authentication. For more information, see the Cloud Translation Setup .

Also, check that your source and target languages are supported by adaptive translation.

Data requirements and suggestions

If you create a dataset or use the Google Cloud console, you must provide example translations in a TSV or TMX file . The examples must be sentence pairs in your intended source and target languages. We recommend that you provide examples that cover the vocabulary, usage, and grammatical quirks of your domain. For additional tips, see Data preparation in the AutoML Translation documentation.

Your data must include at least 5 sentence pairs and no more than 10,000 pairs if you use the console and no more than 30,000 pairs if you use the API. A segment pair can be at most 512 characters (total).

Limitations

• You can translate to only one target language at a time.
• Adaptive translation has limits on the number of input and output characters. For more information, see the Adaptive translation limits on the Quotas page.

Request translations

For translations, the input can be plain text or HTML. Cloud Translation doesn't translate any HTML tags in the input, only text that appears between the tags. The output retains the (untranslated) HTML tags, with the translated text between the tags to the extent possible due to differences between the source and target languages.

POST https://translation.googleapis.com/v3/projects/ PROJECT_ID 
/locations/ LOCATION 
:adaptiveMtTranslate

{
  "referenceSentenceConfig": {
    "referenceSentencePairLists": [
      {
        "referenceSentencePairs": [{
          "sourceSentence": REFERENCE_SOURCE_1_1 
,
          "targetSentence": REFERENCE_TARGET_1_1 
},
        {
          "sourceSentence": REFERENCE_SOURCE_1_2 
,
          "targetSentence": REFERENCE_SOURCE_1_2 
}]
      }
    ],
    "sourceLanguageCode": SOURCE_LANGUAGE 
,
    "targetLanguageCode": TARGET_LANGUAGE 
}
  "content": [" SOURCE_TEXT 
"],
  "mimeType": " MIME_TYPE 
"
}

curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "x-goog-user-project: PROJECT_NUMBER_OR_ID 
" \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
"https://translation.googleapis.com/v3/projects/ PROJECT_ID 
/locations/ LOCATION 
:adaptiveMtTranslate"

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred"; "x-goog-user-project" = " PROJECT_NUMBER_OR_ID 
" }

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://translation.googleapis.com/v3/projects/ PROJECT_ID 
/locations/ LOCATION 
:adaptiveMtTranslate" | Select-Object -Expand Content

{
  "translations": [
    {
      "translatedText": " TRANSLATED_TEXT 
"
    }
  ],
  "languageCode": " TARGET_LANGUAGE 
"
}

 /** Translates using AdaptiveMt. */ 
 private 
  
 static 
  
 void 
  
 adaptiveMtTranslate 
 ( 
  
 TranslationServiceClient 
  
 translationServiceClient 
 , 
  
 String 
  
 projectId 
 , 
  
 String 
  
 sourceLang 
 , 
  
 String 
  
 targetLang 
 , 
  
 Pair<String 
 , 
  
 String 
>  
 referencePairs 
 ) 
  
 { 
  
 ReferenceSentencePairList 
  
 refList 
  
 = 
  
 ReferenceSentencePairList 
 . 
 newBuilder 
 (); 
  
 for 
  
 ( 
 Pair<String 
 , 
  
 String 
>  
 referencePair 
 : 
  
 referencePairs 
 ) 
  
 { 
  
 ReferenceSentencePair 
  
 refPair 
  
 = 
  
 ReferenceSentencePair 
 . 
 newBuilder 
 () 
  
 . 
 setSourceSentence 
 ( 
 referencePair 
 . 
 getKey 
 ()) 
  
 . 
 setTargetSentence 
 ( 
 referencePair 
 . 
 getValue 
 ()); 
  
 refList 
 . 
 addReferenceSentencePair 
 ( 
 refPair 
 ); 
  
 } 
  
 AdaptiveMtTranslateRequest 
  
 request 
  
 = 
  
 AdaptiveMtTranslateRequest 
 . 
 newBuilder 
 () 
  
 . 
 setParent 
 ( 
 LocationName 
 . 
 of 
 ( 
 projectId 
 , 
  
 "us-central1" 
 ). 
 toString 
 ()) 
  
 . 
 setSourceLanguageCode 
 ( 
 sourceLang 
 ) 
  
 . 
 setTargetLanguageCOde 
 ( 
 targetLang 
 ) 
  
 . 
 addReferenceSentencePairLists 
 ( 
 refList 
 ) 
  
 . 
 build 
 (); 
  
 AdaptiveMtTranslateResponse 
  
 response 
  
 = 
  
 translationServiceClient 
 . 
 adaptiveMtTranslate 
 ( 
 request 
 ); 
  
 System 
 . 
 out 
 . 
 println 
 ( 
 "Translating using AdaptiveMt" 
 ); 
  
 System 
 . 
 out 
 . 
 println 
 ( 
 response 
 ); 
 } 

 async 
  
 function 
  
 translate 
 () 
  
 { 
  
 const 
  
 request 
  
 = 
  
 { 
  
 parent 
 : 
  
 `projects/ 
 ${ 
 projectId 
 } 
 /locations/ 
 ${ 
 location 
 } 
 ` 
 , 
  
 referenceSentenceConfig 
 : 
  
 { 
  
 referenceSentencePairLists 
 : 
  
 [ 
  
 { 
  
 referenceSentencePairs 
 : 
  
 [{ 
  
 sourceSentence 
 : 
  
 'Sample reference source 1' 
  
 targetSentence 
 : 
  
 'Sample reference target 1' 
  
 }, 
  
 { 
  
 sourceSentence 
 : 
  
 'Sample reference source 2' 
  
 targetSentence 
 : 
  
 'Sample reference target 2' 
  
 }] 
  
 } 
  
 ], 
  
 sourceLanguageCode 
 : 
  
 'en' 
  
 targetLanguageCode 
 : 
  
 'ja' 
  
 }, 
  
 content 
 : 
  
 [ 
 'Sample translate query' 
 ] 
  
 } 
  
 const 
  
 [ 
 response 
 ] 
  
 = 
  
 await 
  
 translationClient 
 . 
 adaptiveMtTranslate 
 ( 
 request 
 ) 
  
 console 
 . 
 log 
 ( 
 'Translating' 
 ) 
  
 console 
 . 
 log 
 ( 
 response 
 ) 
 }