コンテンツの翻訳

Cloud Translation - Advanced API の使用

モデルを適切にトレーニングしたら、Cloud Translation - Advanced API translateText メソッドでコンテンツの翻訳ができるようになります。Cloud Translation - Advanced API は、用語集と一括翻訳リクエストの使用に対応しています。

REST とコマンドライン

プロジェクトで Cloud AutoML API が有効になっていることを確認します。これは、AutoML API で AutoML モデルを使用する場合に必要です。API を有効にするには、このスタートガイドをご覧ください。

後述のリクエストのデータを使用する前に、次のように置き換えます。

  • project-number-or-id: Google Cloud プロジェクト番号または ID

HTTP メソッドと URL: 

POST https://translation.googleapis.com/v3/projects/project-number-or-id/locations/us-central1:translateText

JSON 本文のリクエスト: 

{
  "model": "projects/project-number-or-id/locations/us-central1/models/TRL1395675701985363739",
  "sourceLanguageCode": "en",
  "targetLanguageCode": "ru",
  "contents": ["Dr. Watson, please discard your trash. You've shared unsolicited email with me.
  Let's talk about spam and importance ranking in a confidential mode."]
}

リクエストを送信するには、次のいずれかのオプションを選択します。

curl

リクエスト本文を request.json という名前のファイルに保存して、次のコマンドを実行します。 

curl -X POST \
-H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
https://translation.googleapis.com/v3/projects/project-number-or-id/locations/us-central1:translateText

PowerShell

リクエスト本文を request.json という名前のファイルに保存して、次のコマンドを実行します。 

$cred = gcloud auth application-default print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
  -Method POST `
  -Headers $headers `
  -ContentType: "application/json; charset=utf-8" `
  -InFile request.json `
  -Uri "https://translation.googleapis.com/v3/projects/project-number-or-id/locations/us-central1:translateText
" | Select-Object -Expand Content

次のような JSON レスポンスが返されます。

{
  "translation": {
    "translatedText": "Доктор Ватсон, пожалуйста, откажитесь от своего мусора.
    Вы поделились нежелательной электронной почтой со мной. Давайте поговорим о
    спаме и важности рейтинга в конфиденциальном режиме.",
    "model": "projects/project-number/locations/us-central1/models/TRL1395675701985363739"
  }
}

Go

import (
	"context"
	"fmt"
	"io"

	translate "cloud.google.com/go/translate/apiv3"
	translatepb "google.golang.org/genproto/googleapis/cloud/translate/v3"
)

// translateTextWithModel translates input text and returns translated text.
func translateTextWithModel(w io.Writer, projectID string, location string, sourceLang string, targetLang string, text string, modelID string) error {
	// projectID := "my-project-id"
	// location := "us-central1"
	// sourceLang := "en"
	// targetLang := "fr"
	// text := "Hello, world!"
	// modelID := "your-model-id"

	ctx := context.Background()
	client, err := translate.NewTranslationClient(ctx)
	if err != nil {
		return fmt.Errorf("NewTranslationClient: %v", err)
	}
	defer client.Close()

	req := &translatepb.TranslateTextRequest{
		Parent:             fmt.Sprintf("projects/%s/locations/%s", projectID, location),
		SourceLanguageCode: sourceLang,
		TargetLanguageCode: targetLang,
		MimeType:           "text/plain", // Mime types: "text/plain", "text/html"
		Contents:           []string{text},
		Model:              fmt.Sprintf("projects/%s/locations/%s/models/%s", projectID, location, modelID),
	}

	resp, err := client.TranslateText(ctx, req)
	if err != nil {
		return fmt.Errorf("TranslateText: %v", err)
	}

	// Display the translation for each input text provided
	for _, translation := range resp.GetTranslations() {
		fmt.Fprintf(w, "Translated text: %v\n", translation.GetTranslatedText())
	}

	return nil
}

Java

import com.google.cloud.translate.v3.LocationName;
import com.google.cloud.translate.v3.TranslateTextRequest;
import com.google.cloud.translate.v3.TranslateTextResponse;
import com.google.cloud.translate.v3.Translation;
import com.google.cloud.translate.v3.TranslationServiceClient;
import java.io.IOException;

public class TranslateTextWithModel {

  public static void translateTextWithModel() throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "YOUR-PROJECT-ID";
    // Supported Languages: https://cloud.google.com/translate/docs/languages
    String sourceLanguage = "your-source-language";
    String targetLanguage = "your-target-language";
    String text = "your-text";
    String modelId = "YOUR-MODEL-ID";
    translateTextWithModel(projectId, sourceLanguage, targetLanguage, text, modelId);
  }

  // Translating Text with Model
  public static void translateTextWithModel(
      String projectId, String sourceLanguage, String targetLanguage, String text, String modelId)
      throws IOException {

    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests. After completing all of your requests, call
    // the "close" method on the client to safely clean up any remaining background resources.
    try (TranslationServiceClient client = TranslationServiceClient.create()) {
      // Supported Locations: `global`, [glossary location], or [model location]
      // Glossaries must be hosted in `us-central1`
      // Custom Models must use the same location as your model. (us-central1)
      String location = "us-central1";
      LocationName parent = LocationName.of(projectId, location);
      String modelPath =
          String.format("projects/%s/locations/%s/models/%s", projectId, location, modelId);

      // Supported Mime Types: https://cloud.google.com/translate/docs/supported-formats
      TranslateTextRequest request =
          TranslateTextRequest.newBuilder()
              .setParent(parent.toString())
              .setMimeType("text/plain")
              .setSourceLanguageCode(sourceLanguage)
              .setTargetLanguageCode(targetLanguage)
              .addContents(text)
              .setModel(modelPath)
              .build();

      TranslateTextResponse response = client.translateText(request);

      // Display the translation for each input text provided
      for (Translation translation : response.getTranslationsList()) {
        System.out.printf("Translated text: %s\n", translation.getTranslatedText());
      }
    }
  }
}

Node.js

/**
 * TODO(developer): Uncomment these variables before running the sample.
 */
// const projectId = 'YOUR_PROJECT_ID';
// const location = 'us-central1';
// const modelId = 'YOUR_MODEL_ID';
// const text = 'text to translate';

// Imports the Google Cloud Translation library
const {TranslationServiceClient} = require('@google-cloud/translate');

// Instantiates a client
const translationClient = new TranslationServiceClient();
async function translateTextWithModel() {
  // Construct request
  const request = {
    parent: `projects/${projectId}/locations/${location}`,
    contents: [text],
    mimeType: 'text/plain', // mime types: text/plain, text/html
    sourceLanguageCode: 'en',
    targetLanguageCode: 'ja',
    model: `projects/${projectId}/locations/${location}/models/${modelId}`,
  };

  try {
    // Run request
    const [response] = await translationClient.translateText(request);

    for (const translation of response.translations) {
      console.log(`Translated Content: ${translation.translatedText}`);
    }
  } catch (error) {
    console.error(error.details);
  }
}

translateTextWithModel();

PHP

use Google\Cloud\Translate\V3\TranslationServiceClient;

$translationServiceClient = new TranslationServiceClient();

/** Uncomment and populate these variables in your code */
// $modelId = '[MODEL ID]';
// $text = 'Hello, world!';
// $targetLanguage = 'fr';
// $sourceLanguage = 'en';
// $projectId = '[Google Cloud Project ID]';
// $location = 'global';
$modelPath = sprintf(
    'projects/%s/locations/%s/models/%s',
    $projectId,
    $location,
    $modelId
);
$contents = [$text];
$formattedParent = $translationServiceClient->locationName(
    $projectId,
    $location
);

// Optional. Can be "text/plain" or "text/html".
$mimeType = 'text/plain';

try {
    $response = $translationServiceClient->translateText(
        $contents,
        $targetLanguage,
        $formattedParent,
        [
            'model' => $modelPath,
            'sourceLanguageCode' => $sourceLanguage,
            'mimeType' => $mimeType
        ]
    );
    // Display the translation for each input text provided
    foreach ($response->getTranslations() as $translation) {
        printf('Translated text: %s' . PHP_EOL, $translation->getTranslatedText());
    }
} finally {
    $translationServiceClient->close();
}

Python


from google.cloud import translate

def translate_text_with_model(
    text="YOUR_TEXT_TO_TRANSLATE",
    project_id="YOUR_PROJECT_ID",
    model_id="YOUR_MODEL_ID",
):
    """Translates a given text using Translation custom model."""

    client = translate.TranslationServiceClient()

    location = "us-central1"
    parent = f"projects/{project_id}/locations/{location}"
    model_path = f"{parent}/models/{model_id}"

    # Supported language codes: https://cloud.google.com/translate/docs/languages
    response = client.translate_text(
        request={
            "contents": [text],
            "target_language_code": "ja",
            "model": model_path,
            "source_language_code": "en",
            "parent": parent,
            "mime_type": "text/plain",  # mime types: text/plain, text/html
        }
    )
    # Display the translation for each input text provided
    for translation in response.translations:
        print("Translated text: {}".format(translation.translated_text))

Ruby

require "google/cloud/translate"

# project_id = "[Google Cloud Project ID]"
# location_id = "[LOCATION ID]"
# model_id = "[MODEL ID]"

# The `model` type requested for this translation.
model = "projects/#{project_id}/locations/#{location_id}/models/#{model_id}"
# The content to translate in string format
contents = ["Hello, world!"]
# Required. The BCP-47 language code to use for translation.
target_language = "fr"
# Optional. The BCP-47 language code of the input text.
source_language = "en"
# Optional. Can be "text/plain" or "text/html".
mime_type = "text/plain"

client = Google::Cloud::Translate.translation_service

parent = client.location_path project: project_id, location: location_id

response = client.translate_text parent:               parent,
                                 contents:             contents,
                                 target_language_code: target_language,
                                 source_language_code: source_language,
                                 model:                model,
                                 mime_type:            mime_type

# Display the translation for each input text provided
response.translations.each do |translation|
  puts "Translated text: #{translation.translated_text}"
end

AutoML Translation の使用

AutoML Translation でカスタムモデルを使用してコンテンツを翻訳することもできます。

ウェブ UI

  1. Google Cloud Console の [AutoML Translation モデル] ページに移動します。

  2. 使用するモデルが別のプロジェクトにある場合は、タイトルバーのプロジェクト セレクタからプロジェクトを選択します。

  3. モデルのリストから、テキストの翻訳に使用するモデルを選択します。

  4. モデルの [予測] タブをクリックします。

  5. テキスト ボックスに翻訳するコンテンツを入力し、[翻訳] をクリックします。

    カスタムモデルの結果と、Cloud Translation - Advanced でデフォルトで使用するベースモデル（Google NMT モデル）を比較します。します。

REST とコマンドライン

後述のリクエストのデータを使用する前に、次のように置き換えます。

  • model-name: モデルの完全な名前。モデルの完全な名前には、プロジェクト名とロケーションが含まれています。モデル名は次の例のようになります。projects/project-id/locations/us-central1/models/model-id
  • source-language-text: 原文の言語からターゲット言語に翻訳するテキスト。

HTTP メソッドと URL: 

POST https://automl.googleapis.com/v1/model-name:predict

JSON 本文のリクエスト: 

{
  "payload" : {
     "textSnippet": {
        "content": "source-language-text"
      }
  }
}

リクエストを送信するには、次のいずれかのオプションを選択します。

curl

リクエスト本文を request.json という名前のファイルに保存して、次のコマンドを実行します。 

curl -X POST \
-H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
https://automl.googleapis.com/v1/model-name:predict

PowerShell

リクエスト本文を request.json という名前のファイルに保存して、次のコマンドを実行します。 

$cred = gcloud auth application-default print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
  -Method POST `
  -Headers $headers `
  -ContentType: "application/json; charset=utf-8" `
  -InFile request.json `
  -Uri "https://automl.googleapis.com/v1/model-name:predict" | Select-Object -Expand Content

次のような JSON レスポンスが返されます。

{
  "payload": [
    {
      "translation": {
        "translatedContent": {
          "content": "target-language-text"
        }
      }
    }
  ]
}

Go

import (
	"context"
	"fmt"
	"io"

	automl "cloud.google.com/go/automl/apiv1"
	automlpb "google.golang.org/genproto/googleapis/cloud/automl/v1"
)

// translatePredict does a prediction for translate.
func translatePredict(w io.Writer, projectID string, location string, modelID string, content string) error {
	// projectID := "my-project-id"
	// location := "us-central1"
	// modelID := "TRL123456789..."
	// content := "text to translate"

	ctx := context.Background()
	client, err := automl.NewPredictionClient(ctx)
	if err != nil {
		return fmt.Errorf("NewPredictionClient: %v", err)
	}
	defer client.Close()

	req := &automlpb.PredictRequest{
		Name: fmt.Sprintf("projects/%s/locations/%s/models/%s", projectID, location, modelID),
		Payload: &automlpb.ExamplePayload{
			Payload: &automlpb.ExamplePayload_TextSnippet{
				TextSnippet: &automlpb.TextSnippet{
					Content:  content,
					MimeType: "text/plain", // Types: "text/plain", "text/html"
				},
			},
		},
	}

	resp, err := client.Predict(ctx, req)
	if err != nil {
		return fmt.Errorf("Predict: %v", err)
	}

	for _, payload := range resp.GetPayload() {
		fmt.Fprintf(w, "Translated content: %v\n", payload.GetTranslation().GetTranslatedContent().GetContent())
	}

	return nil
}

Java

import com.google.cloud.automl.v1.ExamplePayload;
import com.google.cloud.automl.v1.ModelName;
import com.google.cloud.automl.v1.PredictRequest;
import com.google.cloud.automl.v1.PredictResponse;
import com.google.cloud.automl.v1.PredictionServiceClient;
import com.google.cloud.automl.v1.TextSnippet;
import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Paths;

class TranslatePredict {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "YOUR_PROJECT_ID";
    String modelId = "YOUR_MODEL_ID";
    String filePath = "path_to_local_file.txt";
    predict(projectId, modelId, filePath);
  }

  static void predict(String projectId, String modelId, String filePath) throws IOException {
    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests. After completing all of your requests, call
    // the "close" method on the client to safely clean up any remaining background resources.
    try (PredictionServiceClient client = PredictionServiceClient.create()) {
      // Get the full path of the model.
      ModelName name = ModelName.of(projectId, "us-central1", modelId);

      String content = new String(Files.readAllBytes(Paths.get(filePath)));

      TextSnippet textSnippet = TextSnippet.newBuilder().setContent(content).build();
      ExamplePayload payload = ExamplePayload.newBuilder().setTextSnippet(textSnippet).build();
      PredictRequest predictRequest =
          PredictRequest.newBuilder().setName(name.toString()).setPayload(payload).build();

      PredictResponse response = client.predict(predictRequest);
      TextSnippet translatedContent =
          response.getPayload(0).getTranslation().getTranslatedContent();
      System.out.format("Translated Content: %s\n", translatedContent.getContent());
    }
  }
}

Node.js

/**
 * TODO(developer): Uncomment these variables before running the sample.
 */
// const projectId = 'YOUR_PROJECT_ID';
// const location = 'us-central1';
// const modelId = 'YOUR_MODEL_ID';
// const filePath = 'path_to_local_file.txt';

// Imports the Google Cloud AutoML library
const {PredictionServiceClient} = require('@google-cloud/automl').v1;
const fs = require('fs');

// Instantiates a client
const client = new PredictionServiceClient();

// Read the file content for translation.
const content = fs.readFileSync(filePath, 'utf8');

async function predict() {
  // Construct request
  const request = {
    name: client.modelPath(projectId, location, modelId),
    payload: {
      textSnippet: {
        content: content,
      },
    },
  };

  const [response] = await client.predict(request);

  console.log(
    'Translated content: ',
    response.payload[0].translation.translatedContent.content
  );
}

predict();

PHP

use Google\Cloud\AutoMl\V1\ExamplePayload;
use Google\Cloud\AutoMl\V1\PredictionServiceClient;
use Google\Cloud\AutoMl\V1\TextSnippet;

/** Uncomment and populate these variables in your code */
// $projectId = '[Google Cloud Project ID]';
// $location = 'us-central1';
// $modelId = 'my_model_id_123';
// $content = 'text to predict';

$client = new PredictionServiceClient();

try {
    // get full path of model
    $formattedName = $client->modelName(
        $projectId,
        $location,
        $modelId);

    // create payload
    $textSnippet = (new TextSnippet())
        ->setContent($content);
    $payload = (new ExamplePayload())
        ->setTextSnippet($textSnippet);

    // predict with above model and payload
    $response = $client->predict($formattedName, $payload);
    $annotations = $response->getPayload();

    // display results
    foreach ($annotations as $annotation) {
        $translatedContent = $annotation->getTranslation()
            ->getTranslatedContent();
        printf('Translated content: %s' . PHP_EOL, $translatedContent->getContent());
    }
} finally {
    $client->close();
}

Python

このサンプルコードを実行するには、あらかじめ Python クライアント ライブラリをインストールしておく必要があります。

  • model_full_id パラメータは、モデルの完全な名前です。例: projects/434039606874/locations/us-central1/models/3745331181667467569。
from google.cloud import automl

# TODO(developer): Uncomment and set the following variables
# project_id = "YOUR_PROJECT_ID"
# model_id = "YOUR_MODEL_ID"
# file_path = "path_to_local_file.txt"

prediction_client = automl.PredictionServiceClient()

# Get the full path of the model.
model_full_id = automl.AutoMlClient.model_path(
    project_id, "us-central1", model_id
)

# Read the file content for translation.
with open(file_path, "rb") as content_file:
    content = content_file.read()
content.decode("utf-8")

text_snippet = automl.TextSnippet(content=content)
payload = automl.ExamplePayload(text_snippet=text_snippet)

response = prediction_client.predict(name=model_full_id, payload=payload)
translated_content = response.payload[0].translation.translated_content

print(u"Translated content: {}".format(translated_content.content))