What is the best practice on using question marks in case of questions in Dialogflow's training phrases - should I use them or not?
My observation is that if I will add training phrases with question mark (eg. "What is the weather?") then sometimes same user sentences without question mark won't be recognized as specific intent. On the other hand when I will add training phrases without question marks, they will be properly recognized regardless of using question mark.
Example 1
Training phrase: "What is the weather?"
User question: "What is the weather?" (recognized)
User question: "What is the weather" (not recognized)
Example 2
Training phrase: "What is the weather"
User question: "What is the weather?" (recognized)
User question: "What is the weather" (recognized)
Related
I am trying to build a chatbot using Google Dialogflow. I have a set of 100 utterances with me for different Intents. How can I select the training phrases out of this 100 utterance list? Is there any rule to select the unique patterns from the list on the basis of entity pattern or unique paraphrase?
It would be very helpful if you could share the answer here.
Thanks!
Training phrases are example phrases for what end-users might type or say, referred to as end-user expressions. For each intent, you create many training phrases. When an end-user expression resembles one of these phrases, Dialogflow matches the intent.
For example, the training phrase "I want pizza" trains your agent to recognize end-user expressions that are similar to that phrase, like "Get a pizza" or "Order pizza".
You don't have to define every possible example, because Dialogflow's built-in machine learning expands on your list with other, similar phrases. You should create at least 10-20 (depending on complexity of intent) training phrases and try to include more unique training phrases which are relevant to that specific Intent, so your agent can recognize a variety of end-user expressions.
Reference link :https://cloud.google.com/dialogflow/es/docs/intents-training-phrases
I have few intents which are getting trigger on the inappropriate User input. Below are a few examples.
Intent 1). Training phrases I have given
When will I get a job abroad?
Is there any possibility that I will be settled in foreign
When will I settle in foreign
This intent is getting called for user input I had a fight with my friend, will it settle down
Intent 2). Training phrases I have given
When my financial problems will over
Tell me about my financial condition
How will be my financial condition in the future
What will be my financial condition
This intent is getting called for user input When my family problems will over
Please help me out to handle these scenarios.
According to this documentation, you should use at least 10-20 trainning phrases.
You don't have to define every possible example, because Dialogflow's
built-in machine learning expands on your list with other, similar
phrases. You should create at least 10-20 (depending on complexity of
intent) training phrases, so your agent can recognize a variety of
end-user expressions. For example, if you want your intent to
recognize an end-user's expression about their favorite color, you
could define the following training phrases:
"I like red"
"My favorite color is yellow"
"black"
"Blue is my favorite"
...
Given that, to increase the assertiveness of your intents I'd recommend you creating more training phrases and focus them in the main terms necessary in your problem.
I've go a question about the name of an NLP task - Splitting up a complex sentence into simple ones.
For example, if I have this sentence:
"Input t on the username input box and password input box."
I'd like to split this sentence into simpler sentences:
"Input t on the username input box"
"Input t on the password input box"
What would this problem be called? I've tried clause extraction here but I don't want clauses, but rather, fully formed sentences. I've also tried 'sentence simplification' but it exceeds what I'm trying to do, with its lexical simplification and all.
Thanks
I don't think there is the name used by everyone but, for example, in this paper https://arxiv.org/pdf/1805.01035 they call it split-and-rephrase (in several other papers this term is used too).
I have an important question, at the moment i am writing my last essay before starting with my bachelor thesis. It is about voice apps, which includes the google actions for sure.
But i need some informations about the word tolerance of the training phrases. And I was not able to find some information on the internet yet. Does Google only recognize the training phrases typed in by the developer or can Google add some phrases by time or with training (so that the user can say different phrases to trigger an intent which were not typed in from the developer in the beginning) ?
It is really important for my essay. So I would be very happy if you can help me with this question.
I wish you a nice weekend!
Dialogflow uses the training phrases to build a machine-learning algorithm to match similar phrases that aren't exactly what you enter.
For example, the training phrase "I want pizza" trains your agent to recognize end-user expressions that are similar to that phrase, like "Get a pizza" or "Order pizza".
I've made an intent to detect user's answer when they say, for example "when shop is closed" where "closed" is an entity.
When I give the input exactly the same as my training phrase, "when shop is closed", everything is working as expected and and dialogflow correctly detected the intent and the entity value (as shown in the second screenshot).
However, when I input a slight variant to the training phrase, by adding extra words "I think" in front of the sentence, dialogflow still correctly detected the intent, but however this time the parameter value is empty. (as shown in first screenshot)
I will need the value to be detected in both cases, and can't figure out why this is happening.
Screenshot 1
Screenshot 2
Google has published best practices for conversation design here, which should help:
https://developers.google.com/actions/assistant/basics
In this case, have you tried adding, "When is the shop closed?" as a training phrase? Clarifying verb tenses and sentence structure might help Dialogflow correctly identify the parameters you're hoping to extract from a user's given intent.