im new on dialogflow
Dialogflow intents with and without question
i already read this question, but its not answer my question.
so my requirement is like this
I have 100 paragraphs
I want to put 100 paragraphs to database
when the user asks something, the engine will automatically answer by looking for answers in the 100 paragraphs earlier
example:
I have 100 paragraphs about PHP programming learning materials
I input all the learning materials into the database
I asked how to replace the string? then the engine will answer by looking for answers in those 100 paragraphs
so my requirement is engine that without training phrases, the answers can be automatically searched in those 100 paragraphs.
is this possible in dialogflow?
Related
I'm currently working on a bot that helps a user fill in a form in a conversational way. I'm wondering if I should pick LUIS or azure text analytics for this. Or maybe both? Since I'll need to respond to certain intents but answering a question obviously has no intent. Or can I count answering a question as an intent. Either way I'll have to deal with various types of answers ranging from well ranges to names, dates and sentiments. And to add to this: it'll need to support dutch.
Simple example:
Bot asks:
On a scale of 1 - 10 how do you feel about some subject?
User responds:
Well I would give it a 10
Bot extracts:
feelingScore = 10
More complex example
Bot asks:
How do you feel about some subject?
User responds:
Well I would give it a 10
Bot extracts:
feeling = "10"
User responds:
I honestly didn't feel that good about it.
Bot extracts:
feeling = "not that good" (or possibly a sentiment score)
Since there's no action based on user's input, I don't see a reason for using LUIS. You can achieve what you want using Text Analytics.
PS: Please notice that even tough users reply with a 10, the sentiment analysis may not be 100%.
Example:
"I will give it a 10" -> sentiment score is 95
"Well I would give it a 10" -> sentiment score is 85
But at the same time, you can check the NAMED ENTITIES and get the extracted number from it (when provided in the answer)
https://azure.microsoft.com/en-us/services/cognitive-services/text-analytics/
I have a chat data of shape 500k rows. I want to replace or substitute multiple words entity [eg. NEW YORK, New York, new york, Newyork] with single entity as "New York" using python.
I tried to do this using regex, but it consumes too much time for processing. Also I have many such words. Is there any alternative method which consumes less time using Python?
Is there any good resource to study more about Spacy and Rasa API?
You can provide, some simple example of you need to do? I mean example using some training object. You need to change the entity name or entity value?
About more docs to study rasa and spacy, both has a good documentations on his own domains(site/github).
About Rasa, you can find good things here:
https://rasa.com/docs/nlu/
https://medium.com/rasa-blog
https://forum.rasa.com/
About SpaCy:
https://spacy.io/usage/
https://explosion.ai/blog/
Also, you can find more real examples on medium's posts
I am trying to make an automated chatbot using wit.ai
Till now I have learned that we can add intent and entity so chatbot can better understand the question.
I have a dataset of questions and answers.
1) If there is any way by which I can set answers corresponding to a question(or similar questions) in wit, and how do we set these answers?
for example :
if a user asks:
what is a phone?
then our bot should reply the answer which is set by us.
2) if there is any other platform where we can add our dataset of questions and answers to make a chatbot?
1) No, you can't! Since wit.ai is working based on intent classification and entity extraction. You can just learn wit bot to detect intent of a query (for example intent can be restaurant search, or greeting). Then you can return any desired answers in your side.
2) Almost all platforms are based on intent and entity. You should got for QA bots, like DeepQA.
Try Quinto
You can create question-answer formats there.
You can use google dialogflow for this one, https://dialogflow.com/
Since StackOverflow comes with a wealth of questions and user-contributed tags, I am looking at it as an interesting, richly annotated, text corpus for NLP (natural language processing) tasks.
Basically, I want to automatically predict question tags based on the questions body. I am sure this can be done to a certain extend, and there's a number of nice use cases, such as tag suggestions (e.g. to make tag usage more consistent), to name just one.
For this I would need a lot - or even better: - all questions along with their body text and user tags to train a tag predicter with machine learning algorithms.
I know there's the StackOverflow API, but the amount of data I can fetch through it seems to be very limited - for good reasons of course.
So the question is: Is there a way to fetch/download all questions along with their user-tags from StackOverflow?
You can get the data dump at http://www.clearbits.net/torrents/2076-aug-2012, sans the meta sites, a minor oversight which has been fixed with an alternate release, but is not applicable to your request.
What is the flow to create questions for a quiz that allows Categorized Random Questions in Quiz 4.x module? I cannot find any documentation at all in this regard.
Saving a quiz with that option takes me to the 'Manage Questions' page with an 'Add a category' option. Trying to add any new category (that I intend to associate with my questions later) throws a 'The term name you entered doesn't match any registered question terms'error. What are the registered question terms and where do I see them/create them?
You need to go in Drupal (i use v6.19, Quiz v4.0) to Administer/Content management/Taxonomy and create a vocabulary (eg Question Category), within that you can create terms (eg simple, medium, hard).
Then in question Edit, you should see a new drop down - question category, and select simple, med, or hard for that question.
once you have done that for a few questions, go to your quiz and select Categorized random questions under Randomize Questions. Then you will be asked to allocate the no of simple questions etc
it looks very flexible to me and is exactly what we need.