Entity annotation helps to extract useful data from the user inputs. Information is captured based on specific entity types such as time, location, currencies, other user details, etc. You can include these entities in the training examples or intents. The messaging bot detects these entity types, extracts the values, and triggers the user action/ information to complete the flow.
MARK ENTITIES automatically annotates all the entities in the selected intents, instead of the user selecting individual entities for each training example. Mark entities implement the list of existing entities that are visible in the Entity Type tab.
In the training example, only the words that match with the keywords and the synonyms of the entities are annotated. This reduces the user’s time and effort to annotate several entity keywords and synonyms manually and improves intent prediction accuracy.
As you can translate the entities in other regional languages, this auto-triggers the Mark Entities, the existing entities are annotated in the selected languages. By default, this also archives all the marked entities that are translated into different languages. You use this to mark the entities for the selected languages to create a diversified conversational experience.
For more information on Entity Annotation, see Data Extraction .
Topic Matching helps to predict and then classify untrained data for further topic classification. These classifications are based on topic labeling, sentiments analysis, profanity detection, and spam detection. Topic classification organizes unstructured data as similar to the Intent classification and does not require training data.
In Khoros Flow, topic matching is initiated when Intent Classification fails to match with the user utterance. Some of the typical use cases for topic matching are:
Listening bots (Agent Assist)
Conditional fallback routing to human agents
Flow matching (in addition to intents)
With Topic Matching you can find any topic regardless of being implemented in a flow as a trigger or condition unless the Topic matching option is disabled.
Enable Topic Matching
When the Enable topic matching is disabled the classification system can simply skip topic classification.
Note: The Enable topic matching option is disabled, by default, for existing projects and should be turned on for new projects (languages).
In a Flow, click Configuration.
Select the Enable topic matching option. You can also translate topics for the selected Language .
Like with Intent, topics can be disabled individually. When a topic is disabled, its statements, subjects, etc are no longer used in classification. Disabling the topic matching will result in the following:
The topic overview screen to be hidden
The topic trigger will not be shown
The topic match rule for conditions will not be visible
Like with intents, topics can be managed within a separate view named Topics. You can not remove a topic when it is included in a Flow or condition.
With this release, Topics can be grouped like flows and entities. Each topic should have a logical name and statements when newly created. The statement should have a rule that defaults to the This message is about . The Subject of the rule will have the same value as used for the name of the topic. A topic can have multiple different statements, each statement can have multiple rules.
If all rules of a statement match, the topic is matched with a higher Confidence score that defines the accuracy of the topic matched. With Natural Language Processing (NLP), the topic matching will have its confidence level slider. The default value should be 90%. The range is between 1 and 99%.
Like with intent recognition, you can match flows based on topic classification.
In a Flow, drag and drop the Topic trigger.
Enter a logical topic name.
Click Topics in the left panel.
Click + to add a topic.
Select either This message is about , Sentiments or Custom from the Hypothesis drop-down list.
Enter the Subject .
Select the Confidence level for the topic.
Click Save .
A Topic can also be used to match conditions. A perfect example is the use of topic matching when combined with an Unknown . You can add flow level conditions to match the topics. You can choose Topic as a rule for conditions.
You can also translate topics for the selected language. If Topic match is enabled for one language, it should be enabled for any other language as well. In other words, you cannot enable it for some specific languages.
In a Flow, click Configuration.
Click + to add more languages.
Click Translate to automatically translate the topics.
Select the translation language and region.
Click Start Translation.
The topics will be displayed in a new language tab.