Difference between IBM Watson Conversation and Natural Language Understanding
I am building a watson conversation service and I want to know what you know about Wasson Conversation and Natural Language Understanding services.
I think Watson support supports natural language understanding like intent, entity, but Natural Language Understanding service also provides intent and entity.
If I just use intent and entity for conversation, do I need to associate natural language understanding with the conversation service or not?
Thank.
source to share
The conversation service is separate from the NLU. Talk about creating a chatbot on your own domain. Objects / Entities are only what you train and dialogue is a feature only available in conversation, not NLU.
NLU is a preprocessed service that returns various information about the text, but does nothing with the response and will return you what it was preprocessed for. Out of the box, you cannot change this. You can use a product like Watson Knowledge Studio to train a custom annotator, but NLU itself knows it knows and this is it.
It is not necessary to combine them, but it is possible. Depending on what problem you try to solve, you can help you with what you want to use. If you want to understand unstructured text data, without real-time training, NLU is right for you. If you want to develop a chatbot to help your users with some problems, conversation is right for you.
If you want to build a chatbot about generic things, or if you need things like name people, fetch places around the world, etc. and respond accordingly, you can use NLU to fetch metadata and then pipe that to the Chat "and combined with your intentions / entities / dialogue have a more powerful dialogue.
source to share
From the moment I understand this question, I assume that you know that Watson Conversation and Natural Language Classifiers (NLC) are two different services provided by IBM Watson.
Watson Conversation will basically help you build a chatbot or bot (which has speech in text or vice versa). This chatbot helps users in different ways. Let's say if a user asks a question to a chatbot, the chatbot will respond appropriately (it depends on how you designed the dialogs / responses) to the question asked.
Question 1: What is your name?
Answer 1: I Watson.
Instead, if the question is asked incorrectly.
Invalid question: Wat is the name of hurray?
The answer will be: I am Watson.
To build a chatbot using a Watson session, you need to make sure you have the correct understanding of Intents, Entities, and most importantly, Dialogs. (Conversations help you design the flow of conversation) If you know these 3 parts, then it will be helpful for you to speak with Watson. There is no connection between NLC and Watson if you keep them isolated. * As the saying goes, Watson's conversation itself has a natural language understanding, where he could clarify the User's questions, even if the questions ** are incomplete, grammatically incorrect, incorrectly spelled words, etc. *
In short, you don't need to communicate anything (natural language) to start a conversation. Just focus on those 3 (Preferences, Entities and Dialogues) that are provided and you are good to go.
source to share