AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |
Back to Blog
Rasa github2/19/2023 ![]() My email is training data is called NLU data, and it houses the phrases and dialogues ( intents) we expect from a user. Let’s handle the following cases for the supply_contact_info intent. For the purpose of this post, there are three files that we would be discussing: We’ll go file by file, to make it easier to follow. It's, of course, impossible to cover every scenario but we can teach a chatbot the most common ones, making sure we add generic words and phrases that may represent a good portion of messages the bot is likely to see.Īs you can probably guess, this is more of an iterative process, where we evaluate our bot’s performance in the real world and use that to improve its performance. Our goal is to provide varied data so the bot can understand some associations between words, like what follows the word “email” is probably going to be an email id, or that words of the form would be an email. Nor does it know that John is probably a name and that emails contain the symbol. It's easy for us since we get the semantics of natural languages, but a chatbot can’t do that. Returning to our question of how to create bots that can extract useful information in multiple forms. My email is bot: Thanks John for the info! (bot classifies this message as "greet") bot: Hello! Could you please provide your contact information? user: Sure. In our example, when the user greeted the bot, it understand the message as such and responded appropriately by saying hello, and asking for their contact details.Ĭontinuing with our sample conversation, after the bot provides their information, let’s say we program the bot to say “thanks” after the user provides their details. Naturally, for a bot to give an appropriate response, it has to figure out what the user is trying to say. Responses are what the bot says to the user. How we’ll set these slots up, we’ll discuss in a little white. This is because of two properties that are True by default. Since we already have two entities (name and email), we can create slots with the same names, so when names or email-ids are extracted, they are automatically stored in their respective slots. Any information that needs to persist throughout the conversation, like a user’s name or their destination if you were building a flight booking bot, should be stored as slots. The answer to this likes in how good our training data is, and we’ll talk about this in a bit. But how would a chatbot be able to do that? My email is John Doe, can easily extract the names and email ids. name: John Doe email: important question here is: how does the bot know what to extract? A user could potentially enter any combination of information. Let’s say you have defined two entities for name and email. Your bot will extract them depending on the quality of your training data. My email is message above has two pieces of information - the name and the email. The user would then enter their details, like their name and their email id. (bot classifies this message as "greet") bot: Hello! Could you please provide your contact information? (bot classifies this message as "greet") EntitiesĮntities are pieces of data that can be extracted from a user message.Ĭontinuing our example, after the user greets the bot, the bot asks for their contact information. Examples of intents - image by author user: Hi. ![]()
0 Comments
Read More
Leave a Reply. |