AWS SDK または CLI DetectDominantLanguageで を使用する

    using System;
    using System.Threading.Tasks;
    using Amazon.Comprehend;
    using Amazon.Comprehend.Model;

    /// <summary>
    /// This example calls the Amazon Comprehend service to determine the
    /// dominant language.
    /// </summary>
    public static class DetectDominantLanguage
    {
        /// <summary>
        /// Calls Amazon Comprehend to determine the dominant language used in
        /// the sample text.
        /// </summary>
        public static async Task Main()
        {
            string text = "It is raining today in Seattle.";

            var comprehendClient = new AmazonComprehendClient(Amazon.RegionEndpoint.USWest2);

            Console.WriteLine("Calling DetectDominantLanguage\n");
            var detectDominantLanguageRequest = new DetectDominantLanguageRequest()
            {
                Text = text,
            };

            var detectDominantLanguageResponse = await comprehendClient.DetectDominantLanguageAsync(detectDominantLanguageRequest);
            foreach (var dl in detectDominantLanguageResponse.Languages)
            {
                Console.WriteLine($"Language Code: {dl.LanguageCode}, Score: {dl.Score}");
            }

            Console.WriteLine("Done");
        }
    }

入力テキストの主要言語を検出するには

以下の detect-dominant-language は、入力テキストを分析し、主要言語を特定します。事前トレーニング済みモデルの信頼スコアも出力されます。

aws comprehend detect-dominant-language \
    --text "It is a beautiful day in Seattle."

出力:

{
    "Languages": [
        {
            "LanguageCode": "en",
            "Score": 0.9877256155014038
        }
    ]
}

詳細については、「Amazon Comprehend デベロッパーガイド」の「主要言語」を参照してください。

import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.comprehend.ComprehendClient;
import software.amazon.awssdk.services.comprehend.model.ComprehendException;
import software.amazon.awssdk.services.comprehend.model.DetectDominantLanguageRequest;
import software.amazon.awssdk.services.comprehend.model.DetectDominantLanguageResponse;
import software.amazon.awssdk.services.comprehend.model.DominantLanguage;
import java.util.List;

/**
 * Before running this Java V2 code example, set up your development
 * environment, including your credentials.
 *
 * For more information, see the following documentation topic:
 *
 * https://docs.aws.amazon.com/sdk-for-java/latest/developer-guide/get-started.html
 */
public class DetectLanguage {
    public static void main(String[] args) {
        // Specify French text - "It is raining today in Seattle".
        String text = "Il pleut aujourd'hui à Seattle";
        Region region = Region.US_EAST_1;

        ComprehendClient comClient = ComprehendClient.builder()
                .region(region)
                .build();

        System.out.println("Calling DetectDominantLanguage");
        detectTheDominantLanguage(comClient, text);
        comClient.close();
    }

    public static void detectTheDominantLanguage(ComprehendClient comClient, String text) {
        try {
            DetectDominantLanguageRequest request = DetectDominantLanguageRequest.builder()
                    .text(text)
                    .build();

            DetectDominantLanguageResponse resp = comClient.detectDominantLanguage(request);
            List<DominantLanguage> allLanList = resp.languages();
            for (DominantLanguage lang : allLanList) {
                System.out.println("Language is " + lang.languageCode());
            }

        } catch (ComprehendException e) {
            System.err.println(e.awsErrorDetails().errorMessage());
            System.exit(1);
        }
    }
}

class ComprehendDetect:
    """Encapsulates Comprehend detection functions."""

    def __init__(self, comprehend_client):
        """
        :param comprehend_client: A Boto3 Comprehend client.
        """
        self.comprehend_client = comprehend_client


    def detect_languages(self, text):
        """
        Detects languages used in a document.

        :param text: The document to inspect.
        :return: The list of languages along with their confidence scores.
        """
        try:
            response = self.comprehend_client.detect_dominant_language(Text=text)
            languages = response["Languages"]
            logger.info("Detected %s languages.", len(languages))
        except ClientError:
            logger.exception("Couldn't detect languages.")
            raise
        else:
            return languages