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

Text Similarity

  • 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);

TextSimilarityReq req = new TextSimilarityReq();

//Two texts for similarity comparison
req.setText1("text-1");
req.setText2("text-2");

//Supported language of the text. The default value is zh, indicating Chinese. Only Chinese is currently supported.
req.setLang("zh");

try {
    TextSimilarityResp resp = client.getTextSimilarity(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 TextSimilarityReq parameters.
    Table 1 TextSimilarityReq parameters

    Parameter

    Mandatory

    Type

    Description

    text1

    Yes

    String

    Text 1, on which the text similarity is to be computed. The text is encoded using UTF-8 and contains 1 to 512 characters.

    text2

    Yes

    String

    Text 2, on which the text similarity is to be computed. The text is encoded using UTF-8 and contains 1 to 512 characters.

    lang

    No

    String

    Supported text language type. The default value is zh. Currently, only Chinese is supported.
  • Table 2 describes TextSimilarityResp parameters.
    Table 2 TextSimilarityResp parameters

    Parameter

    Type

    Description

    similarity

    Double

    Similarity score. The value ranges from 0 to 1. By default, eight digits are reserved after the decimal point.