{"id":17929,"date":"2016-10-28T17:12:45","date_gmt":"2016-10-28T17:12:45","guid":{"rendered":"https:\/\/developer.kore.com\/?post_type=docs&p=8561"},"modified":"2023-07-24T07:15:18","modified_gmt":"2023-07-24T06:15:18","slug":"testing-your-bot-with-nlp","status":"publish","type":"post","link":"https:\/\/developer.kore.ai\/v10-1\/docs\/bots\/test-your-bot\/testing-your-bot-with-nlp\/","title":{"rendered":"Utterance Testing"},"content":{"rendered":"
\r\n\t
\r\n\t\t
\r\n\t\t\t

To make sure your assistant responds to user utterances with related tasks, it is important that you test it with a variety of user inputs. Evaluating a VA with a large sample of expected user inputs not only provides insights into its responses but also gives you a great opportunity to train it in interpreting diverse human expressions.<\/span><\/p>\n

You can perform all the training-related activities for a VA from the <\/span>Utterance Testing<\/span><\/em> module. We will use a sample <\/span>Travel Planning <\/span><\/em>assistant to provide examples within this article.<\/span><\/p>\n

<\/div><\/div>\n

Testing the Assistant<\/span><\/span><\/h1>\n

Simply put, testing a VA refers to checking if it can respond to a user utterance with the most relevant task. Given the flexibility of language, users will use a wide range of phrases to express the same intent.<\/span><\/p>\n

For example, you can rephrase <\/span>I want to change my ticket from San Francisco to Los Angeles on Jan 1<\/span><\/em> as <\/span>Please change my travel date. Can\u2019t make it on Jan 1. <\/span><\/em>The trick is to train the assistant to map both of these utterances with the same intent.<\/span><\/p>\n

The first step to start testing a VA is to identify a representative sample of user utterances to test the responses. Look for sources of data that reflect real-world usage of the language, such as support chat logs, online communities, FAQ pages of relevant portals.<\/span><\/p>\n

<\/div><\/div>\n

How to test the assistant<\/span><\/span><\/h2>\n

Follow these steps to test your assistant:<\/span><\/p>\n

    \n
  1. Open the assistant that you want to test.<\/span><\/li>\n
  2. Select the <\/span>Build<\/strong> tab from the top menu.<\/span><\/li>\n
  3. From the left menu click <\/span>Testing<\/strong> -> <\/span>Utterance Testing<\/strong>.<\/span><\/li>\n
  4. In the case of a multiple intent model, you can select the <\/span>Intent Model<\/strong> against which you want to test the utterance. The ML Engine will detect the intents only from the selected model.<\/span><\/li>\n
  5. In the <\/span>Type a user utterance<\/strong> field, enter the utterance that you want to test. Example: <\/span>Book a flight<\/span><\/em>.<\/span><\/li>\n
  6. The result appears with a single, multiple, or no matching intents<\/span><\/li>\n<\/ol>\n

    \"\"<\/a><\/span><\/p>\n

    <\/div><\/div>\n

    Types of Test Results<\/span><\/span><\/h2>\n

    When you test an utterance, the NLP engine tries to identify an intent using the following\u00a0 engines and intent identification features:<\/span><\/p>\n