Custom Statement Tags

Custom statement tag classification is the task of classifying an utterance with respect to the function it serves in a dialogue, i.e. the act the speaker is performing. These tags can be configured to detect custom intents by giving example statements.

Example Response

  "status": true,
  "error": {},
  "warning": {},
  "data": {
    "similarityMatch": [
        "statementTagId": "statement-bxllq1zsuzkvuj44go-1636609624728",
        "statementTagName": "compliance-quality-check"
        "matchedTextList": [
            "score": 0.5230883955955505,
            "text": "This call is going to be recorded for quality purposes.",
            "value": "This call will be recorded"

status field will be set to false if something went wrong while processing the request check for any error messages in the error field

warning field will contain any warnings raised to the user while processing the request. For example if the user sends in a request with invalid statement_tag_ids warning field will contain the list of invalid statement_tag_ids

Response Object



The statement tag similarity identified by the models


The statement tag Id against which the sentences are matched


The name of the matching statement tag


The similarity matching score ranges from 0 to 1


The sentence which is used to predict statement tag for


The predicted statement tag

Last updated