À utiliser DetectSyntax avec un AWS SDK ou CLI

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

    /// <summary>
    /// This example shows how to use Amazon Comprehend to detect syntax
    /// elements by calling the DetectSyntaxAsync method.
    /// </summary>
    public class DetectingSyntax
    {
        /// <summary>
        /// This method calls DetectSynaxAsync to identify the syntax elements
        /// in the sample text.
        /// </summary>
        public static async Task Main()
        {
            string text = "It is raining today in Seattle";

            var comprehendClient = new AmazonComprehendClient();

            // Call DetectSyntax API
            Console.WriteLine("Calling DetectSyntaxAsync\n");
            var detectSyntaxRequest = new DetectSyntaxRequest()
            {
                Text = text,
                LanguageCode = "en",
            };
            DetectSyntaxResponse detectSyntaxResponse = await comprehendClient.DetectSyntaxAsync(detectSyntaxRequest);
            foreach (SyntaxToken s in detectSyntaxResponse.SyntaxTokens)
            {
                Console.WriteLine($"Text: {s.Text}, PartOfSpeech: {s.PartOfSpeech.Tag}, BeginOffset: {s.BeginOffset}, EndOffset: {s.EndOffset}");
            }

            Console.WriteLine("Done");
        }
    }

Pour détecter les parties du discours dans un texte saisi

L'detect-syntaxexemple suivant analyse la syntaxe du texte saisi et renvoie les différentes parties du discours. Le score de confiance du modèle préentraîné est également généré pour chaque prédiction.

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

Sortie :

{
    "SyntaxTokens": [
        {
            "TokenId": 1,
            "Text": "It",
            "BeginOffset": 0,
            "EndOffset": 2,
            "PartOfSpeech": {
                "Tag": "PRON",
                "Score": 0.9999740719795227
            }
        },
        {
            "TokenId": 2,
            "Text": "is",
            "BeginOffset": 3,
            "EndOffset": 5,
            "PartOfSpeech": {
                "Tag": "VERB",
                "Score": 0.999901294708252
            }
        },
        {
            "TokenId": 3,
            "Text": "a",
            "BeginOffset": 6,
            "EndOffset": 7,
            "PartOfSpeech": {
                "Tag": "DET",
                "Score": 0.9999938607215881
            }
        },
        {
            "TokenId": 4,
            "Text": "beautiful",
            "BeginOffset": 8,
            "EndOffset": 17,
            "PartOfSpeech": {
                "Tag": "ADJ",
                "Score": 0.9987351894378662
            }
        },
        {
            "TokenId": 5,
            "Text": "day",
            "BeginOffset": 18,
            "EndOffset": 21,
            "PartOfSpeech": {
                "Tag": "NOUN",
                "Score": 0.9999796748161316
            }
        },
        {
            "TokenId": 6,
            "Text": "in",
            "BeginOffset": 22,
            "EndOffset": 24,
            "PartOfSpeech": {
                "Tag": "ADP",
                "Score": 0.9998047947883606
            }
        },
        {
            "TokenId": 7,
            "Text": "Seattle",
            "BeginOffset": 25,
            "EndOffset": 32,
            "PartOfSpeech": {
                "Tag": "PROPN",
                "Score": 0.9940530061721802
            }
        }
    ]
}

Pour plus d'informations, consultez la section Analyse syntaxique dans le manuel Amazon Comprehend Developer Guide.

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.DetectSyntaxRequest;
import software.amazon.awssdk.services.comprehend.model.DetectSyntaxResponse;
import software.amazon.awssdk.services.comprehend.model.SyntaxToken;
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 DetectSyntax {
    public static void main(String[] args) {
        String text = "Amazon.com, Inc. is located in Seattle, WA and was founded July 5th, 1994 by Jeff Bezos, allowing customers to buy everything from books to blenders. Seattle is north of Portland and south of Vancouver, BC. Other notable Seattle - based companies are Starbucks and Boeing.";
        Region region = Region.US_EAST_1;
        ComprehendClient comClient = ComprehendClient.builder()
                .region(region)
                .build();

        System.out.println("Calling DetectSyntax");
        detectAllSyntax(comClient, text);
        comClient.close();
    }

    public static void detectAllSyntax(ComprehendClient comClient, String text) {
        try {
            DetectSyntaxRequest detectSyntaxRequest = DetectSyntaxRequest.builder()
                    .text(text)
                    .languageCode("en")
                    .build();

            DetectSyntaxResponse detectSyntaxResult = comClient.detectSyntax(detectSyntaxRequest);
            List<SyntaxToken> syntaxTokens = detectSyntaxResult.syntaxTokens();
            for (SyntaxToken token : syntaxTokens) {
                System.out.println("Language is " + token.text());
                System.out.println("Part of speech is " + token.partOfSpeech().tagAsString());
            }

        } 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_syntax(self, text, language_code):
        """
        Detects syntactical elements of a document. Syntax tokens are portions of
        text along with their use as parts of speech, such as nouns, verbs, and
        interjections.

        :param text: The document to inspect.
        :param language_code: The language of the document.
        :return: The list of syntax tokens along with their confidence scores.
        """
        try:
            response = self.comprehend_client.detect_syntax(
                Text=text, LanguageCode=language_code
            )
            tokens = response["SyntaxTokens"]
            logger.info("Detected %s syntax tokens.", len(tokens))
        except ClientError:
            logger.exception("Couldn't detect syntax.")
            raise
        else:
            return tokens