Microsoft

How can we improve Microsoft Cognitive Services?

Classify the type of entities (people, location, business, dates)

I enjoyed testing the text analytics API, however I noticed that while the service detects entities, it doesn't appear to classify them. For example, I would expect the service to identify a person from a business or street name. Similarly, can it detect an address such as 123 Elm Street, City, State, Zip. I anticipate that this would be a valuable add-on.

5 votes
Sign in
(thinking…)
Password icon
Signed in as (Sign out)

We’ll send you updates on this idea

Ted Bradley shared this idea  ·   ·  Flag idea as inappropriate…  ·  Admin →

3 comments

Sign in
(thinking…)
Password icon
Signed in as (Sign out)
Submitting...
  • Adminashly.yeo (Senior Program Manager, Microsoft Cognitive Services) commented  ·   ·  Flag as inappropriate

    The new Text Analytics v2.1 release contains an update to Named Entity Recognition that support PERSON, LOCATION and ORGANIZATION types. Although the ADDRESS type is not yet available, a street address is supported as a LOCATION type. For more information please visit https://docs.microsoft.com/en-us/azure/cognitive-services/text-analytics/how-tos/text-analytics-how-to-entity-linking

    Example
    Request:
    POST https://westus2.api.cognitive.microsoft.com/text/analytics/v2.1/entities?showStats= HTTP/1.1
    Connection: close
    Accept-Encoding: gzip,deflate
    Ocp-Apim-Subscription-Key: XXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
    Content-Type: application/json
    Content-Length: 177
    Host: westus2.api.cognitive.microsoft.com
    User-Agent: Apache-HttpClient/4.5.2 (Java/1.8.0_181)

    {
    "documents": [
    {
    "language": "en",
    "id": "1",
    "text": "The accident occurred outside the residence at 2021 S Closson St, Peoria, AZ 99113."
    }
    ]
    }

    Response:
    HTTP/1.1 200 OK
    Transfer-Encoding: chunked
    Content-Type: application/json; charset=utf-8
    x-ms-transaction-count: 1
    CSP-Billing-Usage: CognitiveServices.TextAnalytics.BatchScoring|1
    x-aml-ta-request-id: XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
    X-Content-Type-Options: nosniff
    apim-request-id: XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
    Strict-Transport-Security: max-age=31536000; includeSubDomains; preload
    Date: Wed, 24 Apr 2019 01:47:58 GMT
    Connection: close

    {
    "documents" : [
    {
    "id" : "1",
    "entities" : [
    {
    "name" : "2021",
    "matches" : [
    {
    "entityTypeScore" : 0.8,
    "text" : "2021",
    "offset" : 47,
    "length" : 4
    }
    ],
    "type" : "DateTime",
    "subType" : "DateRange"
    },
    {
    "name" : "2021 S Closson St",
    "matches" : [
    {
    "entityTypeScore" : 0.5,
    "text" : "2021 S Closson St",
    "offset" : 47,
    "length" : 17
    }
    ],
    "type" : "Location"
    },
    {
    "name" : "Peoria, Arizona",
    "matches" : [
    {
    "wikipediaScore" : 0.7520964877869265,
    "entityTypeScore" : 0.8,
    "text" : "Peoria, AZ",
    "offset" : 66,
    "length" : 10
    }
    ],
    "wikipediaLanguage" : "en",
    "wikipediaId" : "Peoria, Arizona",
    "wikipediaUrl" : "https://en.wikipedia.org/wiki/Peoria,_Arizona",
    "bingId" : "a5b68822-539f-4073-b350-66e29a82b95e",
    "type" : "Location"
    },
    {
    "name" : "99113",
    "matches" : [
    {
    "entityTypeScore" : 0.8,
    "text" : "99113",
    "offset" : 77,
    "length" : 5
    }
    ],
    "type" : "Quantity",
    "subType" : "Number"
    }
    ]
    }
    ],
    "errors" : [ ]
    }

Feedback and Knowledge Base