Help Center> Natural Language Processing> SDK Reference> Using the NLP Fundamentals SDK> Calling NLP Fundamentals APIs> Sentence Vector
View PDF

Sentence Vector

  • Example request 
    //You are advised to construct and use the client in a singleton pattern to avoid frequent object creation.
NlpfClient client = new NlpfClient(AuthMode.AKSK,authInfo);

SentenceVectorsReq req = new SentenceVectorsReq();

//Construct a sentence for which a sentence vector needs to be obtained.
List<String> sentences = new ArrayList<String>();
sentences.add("sentence-1");
sentences.add("sentence-2");
req.setSentences(sentences);

//Model name. Only general is supported. 
req.setDomain("general");

try {
    SentenceVectorsResp resp = client.getSentenceVectors(req);
} catch (NlpException e) {
    //A failure is thrown as an exception. For details about exceptions, see section "Exceptions". The client automatically processes exceptions.
}
  • Table 1 describes SentenceVectorsReq parameters.
    Table 1 SentenceVectorsReq parameters

    Parameter

    Mandatory

    Type

    Description

    sentences

    Yes

    List<String>

    Text list. The text is encoded using UTF-8 and contains 1 to 512 characters. The text list contains 1 to 1,000 text data records.

    domain

    No

    String

    Name of the model used for computing the sentence vector. Currently, only the default value general is available.
  • Table 2 describes SentenceVectorsResp parameters.
    Table 2 SentenceVectorsResp parameters

    Parameter

    Type

    Description

    vectors

    List<List<Double>>

    Sentence vector result list. Sentence vectors are returned according to the input sentence sequence.