When I first started learning about chatbots and natural language processing, I found the new vocabulary confusing! But like any technical field, a shared vocabulary makes it easier to communicate efficiently. Here are the 10 terms that I think will be most useful to you. The first 3 are the most important, so here’s a little visual:
Utterance: Anything the user says. For example, if a user types “show me yesterday’s financial news”, the entire sentence is the utterance.
Intent: An intent is the user’s intention. For example, if a user types “show me yesterday’s financial news”, the user’s intent is to retrieve a list of financial headlines. Intents are given a name, often a verb and a noun, such as “showNews”.
Entity: An entity modifies an intent. For example, if a user types “show me yesterday’s financial news”, the entities are “yesterday” and “financial”. Entities are given a name, such as “dateTime” and “newsType”. Entities are sometimes referred to as slots.
Broadcast: A broadcast is a message sent proactively to a user. It is not a response to user input. Also referred to as “subscription messaging”, a broadcast is the chatbot equivalent of a push message in a mobile app.
Channel: Channels are the medium for chatbot conversations. Examples of channels include Facebook Messenger, Skype, Slack and SMS. Email and web chat windows are also mediums.
Conversational UI: User interfaces based on human speech, either written or spoken. Conversational UIs don’t use buttons, links or other graphical elements. Many chatbots, including Tangowork, mix conversational UI with graphical UI.
Natural Language Processing (NLP): NLP examines an utterance and extracts the intent and entities. NLP software includes Amazon Lex, Facebook’s Wit.ai, and Microsoft’s LUIS.
Pilot: The stage of development where the chatbot is deployed to a small group of users for testing. Pilots are especially critical for chatbots, because unlike a web application, the range of possible user input is unlimited.
Proof-of-concept (POC): The stage of development where the chatbot functions properly so long as the input is artificially constrained. A POC demonstrates the potential. POCs are especially useful for emerging technologies that are not fully understood by stakeholders, like chatbots.
Response: Anything the bot says in response to user input.
We’d love to have you at our webinar on Wednesday, Aug 9: Why Chatbots Are the Next Big Thing for Internal Communications. Even if you can’t make the date, register to get a link to the recording.
Chatbot Vocabulary: 10 Chatbot Terms You Need to Know was originally published in Chatbots Magazine on Medium, where people are continuing the conversation by highlighting and responding to this story.