Help Center> Natural Language Processing> API Reference> NLP APIs> NLP Fundamentals APIs> NER (Domain-specific Edition)
View PDF

NER (Domain-specific Edition)

Introduction

This API is used to identify named entities of text. Currently, NER is supported in the general, business, and entertainment domains.

  • General domain: includes entities such as person name, location, organization, time point, date, percentage, currency, ordinal number, quantifier, nationality, occupation, email address, country, and festival.
  • Business domain: includes entities such as company name, brand, job, position, email address, mobile number, telephone number, IP address, ID card number, and website.
  • Entertainment domain: includes entities such as movie name, animation name, book name, Internet-related entity, song name, product name, drama name, and TV program name.

For details about endpoints, see Endpoints.

Calling NLP APIs will incur fees. NLP packages are classified into the basic and domain-specific editions. When purchasing a package, view the APIs supported by the basic package and domain-specific packages in the Natural Language Processing Price Calculator.

URI

  • URI format 
    POST /v1/{project_id}/nlp-fundamental/ner/domain
  • Parameter description
    Table 1 URI parameters

    Parameter

    Mandatory

    Description

    project_id

    Yes

    Project ID. For details about how to obtain the project ID, see Obtaining a Project ID.

Request

Table 2 describes the request parameters.

Table 2 Request parameters

Parameter

Type

Mandatory

Description

text

String

Yes

Text to be analyzed. The text is encoded using UTF-8 and contains 1 to 512 characters.

lang

String

No

Supported language type. Currently, only Chinese is supported. The default value is zh.

domain

String

No

Supported domain type. The value can be general, business, or entertainment. The default value is general.

Response

Table 3 describes the response parameters.

Table 3 Response parameters

Parameter

Type

Description

named_entities

Array of named_entity objects

NER result.

For details, see Table 4.

error_code

String

Error code when the API fails to be called. For details, see Error Code.

The parameter is not included when the API call succeeds.

error_msg

String

Error message returned when the API fails to be called.

The parameter is not included when the API call succeeds.
Table 4 Data structure description of named_entity

Parameter

Type

Description

word

String

Entity text

tag

String

Entity type

  • The general domain includes nr (person name), ns (location), nt (organization), tpt (time point), day (date), pct (percentage), mny, (currency), ord (ordinal number), qtt (quantifier); race (nationality), job, email, coun (country), and fest (festival).
  • The business domain includes com (company name), bra (brand), job, post (position), email, cell (mobile number), tele (telephone number), ip (IP address), id (ID card number), and web (website).
  • The entertainment domain includes mov (movie name), anime (animation name), book (book name), int (Internet-related entity), song (song name), pro (product name), dra (drama name), and tv (TV program name).

offset

Integer

Start position of the entity text in the text to be analyzed

len

Integer

Length of an entity text

Example 1

  • Example request 
    POST https://{endpoint}/v1/{project_id}/nlp-fundamental/ner/domain

Request Header:
    Content-Type: application/json
    X-Auth-Token: MIINRwYJKoZIhvcNAQcCoIINODCCDTQCAQExDTALBglghkgBZQMEAgEwgguVBgkqhkiG...

Request Body:
    {
    "text":"Text for NER",
    "lang":"zh",
    "domain":"general"
    }
  • Example response
    • Successful example response 
      {
    "named_entities": [
        {
            "len": 2,
            "offset": 0,
            "tag": "day",
            "word": "word-1"
        },
        {
            "len": 3,
            "offset": 2,
            "tag": "job",
            "word": "word-2"
        },
        {
            "len": 3,
            "offset": 5,
            "tag": "nr",
            "word": "word-3"
        },
        {
            "len": 2,
            "offset": 10,
            "tag": "ns",
            "word": "word-4"
        },
        {
            "len": 2,
            "offset": 32,
            "tag": "ord",
            "word": "word-5"
        }
    ]
}
    • Failed example response 
      {
    "error_code": "NLP.0301",
    "error_msg": "The length of text should be in the range of 1-512."
}

Example 2

  • Example request 
    POST https://{endpoint}/v1/{project_id}/nlp-fundamental/ner/domain

Request Header:
    Content-Type: application/json
    X-Auth-Token: MIINRwYJKoZIhvcNAQcCoIINODCCDTQCAQExDTALBglghkgBZQMEAgEwgguVBgkqhkiG...

Request Body:
    {
        "text":"Programmer Xiaoming is a Huawei employee. His email address is xiaoming@xx.com and phone number is 12345678.",
    "lang":"zh",
        "domain":"business"
    }
  • Example response
    • Successful example response 
      {
    "named_entities": [
        {
            "len": 3,
            "offset": 0,
            "tag": "job",
            "word": "word-2"
        },
        {
            "len": 2,
            "offset": 6,
            "tag": "com",
          "word": "Huawei"
        },
        {
            "len": 15,
            "offset": 15,
            "tag": "email",
            "word": "xiaoming@xx.com"
        },
        {
            "len": 8,
            "offset": 33,
            "tag": "tele",
            "word": "12345678"
        }
    ]
}
    • Failed example response 
      {
    "error_code": "NLP.0301",
    "error_msg": "The length of text should be in the range of 1-512."
}

Example 3

  • Example request 
    POST https://{endpoint}/v1/{project_id}/nlp-fundamental/ner/domain

Request Header:
    Content-Type: application/json
    X-Auth-Token: MIINRwYJKoZIhvcNAQcCoIINODCCDTQCAQExDTALBglghkgBZQMEAgEwgguVBgkqhkiG...

Request Body:
    {
       "text": "Text for NER",
    "lang":"zh",
        "domain":"entertainment"
    }
  • Example response
    • Successful example response 
      {
    "named_entities": [
        {
            "len": 3,
            "offset": 8,
            "tag": "anime",
            "word": "word-1"
        },
        {
            "len": 2,
            "offset": 18,
            "tag": "song",
            "word": "word-2"
        },
        {
            "len": 4,
            "offset": 25,
            "tag": "pro",
            "word": "word-3"
        },
        {
            "len": 3,
            "offset": 31,
            "tag": "dra",
            "word": "word-4"
        }
    ]
}
    • Failed example response 
      {
    "error_code": "NLP.0301",
    "error_msg": "The length of text should be in the range of 1-512."
}

Status Code

For details about status codes, see Status Code.

Error Code

For details about error codes, see Error Code.

Parent topic: NLP Fundamentals APIs