Edit translations for Virtual Agent topics

A Virtual Agent admin user can edit and publish translations directly in Virtual Agent Designer.

始める前に

注:

An updated Assistant Designer Asset library user interface is available when you install Now Assist in Virtual Agent and turn on the Now Assist Topics skill. This content assumes that you have activated this skill and can see the list view. If this skill is not activated, you see the legacy UI and topics page. For more information, see Virtual Agent Designer legacy topics page.

Role required: virtual_agent_admin or admin

手順

1. Do one of the following:
   • Navigate to All > Conversational Interfaces > Virtual Agent > Designer, open a published topic, and then select the Languages tab.
   • (NLU only) Navigate to All > Conversational Interfaces > Virtual Agent > Designer, and slide the discovery type toggle switch to NLU/keyword. Select Manage languages from Resources, and then choose a model, language, and topic.
2. In the Topic translations column, select Edit.
   The Edit Translations form opens.

   

3. On the Edit Translations form, you can do any of the following:
   • Unlock fields and enter translations directly on the form.
   • If it is configured in the Localization Framework, use machine translation to fill in the fields.

     To set up machine translation, see Create a translator configuration.

   • Export files to send to a third party for translation.

     Select Export Source File, and then choose the file type. Select Export File to begin the download.

   • Import translated files received from a translation service.

     From the Export Source file list, select Import Translated File.

4. When translations are ready to publish, select Publish Translations.

タスクの結果

Once translations are published, they are made available to Virtual Agent topics that use keywords dynamically.

If your topic uses Natural Language Understanding (NLU), train your localized models. You may also need to map them to the topic. Then test and publish your localized models to ensure that native speakers can access localized intents. For more information, see Map a topic to a secondary NLU model and Test topic and NLU model translations.