I am having a problem with NLU of Rasa. I don't understand how NLU preprocessing data module works so I need yours help. Please tell me some information or document about Rasa because the document of rasa so very few. Thanks all.
Related
Is it possible to create a rasa chatbot which trains itself on the basis of user input?
If yes, please suggest me some resources.
The experimental features end-to-end training was recently released in Rasa 2.2
This allows training a model on actual user text and bot responses.
More info here.
I am a new bee to IBM Watson. I went through videos to create virtual assistant/chatbot where we could define intents/entities and answer accordingly. This seems fine when I have limited number of intents/entities. But say, I have a eBook and I want to train Watson to answer from this eBook. How do I achieve this. Anyone high level approach or direction will be really helpful.
There are different approaches.
You could use the integrated search skill which provides a link to Watson Discovery. You would upload your eBook to Watson Discovery and kind of index it.
Another approach is to use a database or something else as backend. Based on the input which identifies the search term and scopes which eBook to search, the answer would be retrieved from the backend database. This tutorial features a Db2 database and Watson Assistant retrieves the answer from the database. A similar approach is taken in this sample which shows how to retrieve excerpts from Wikipedia.
The supported list of transformations in IBM's ETL service DataConnect in Bluemix Cloud are these ones here: https://console.ng.bluemix.net/docs/services/dataworks1/using_operations.html#concept_h4k_5tf_xw
I have looked and looked but with no luck, what if I want to transform some of my data with an operation that is not included here? For example run custom code in a column and get some specific output?
Data Connect does not currently support refine operations outside of those provided with the service. We are adding new features and functionality weekly, but if you have a specific operation in mind, please let us know.
I will find out for you if we have the ability to execute custom code on our roadmap.
Regards,
Wesley - IBM Bluemix Data Connect Engineering
As Wes mentions above in the short term we will continue to add new data preparation and transformation capabilities to the service. Currently there is no extensibility that allows you to code new transformations.
In the longer term we are considering allowing users to edit/extend pipelines using languages like Scala and Python. We don't have a defined date for these new capabilities.
Regards,
Hernando Borda
IBM Bluemix Data Connect Product Manager
Looking at Retrieve and Rank Web UI bound to the conversation-enhanced application:
https://github.com/watson-developer-cloud/conversation-enhanced
no questions have been uploaded for training, though there is a trainingdata.csv.
I would like to understand how trainingdata.csv was constructed.
Thank you !
That training data was created manually, not using the UI, using the approach described in https://www.ibm.com/watson/developercloud/doc/retrieve-rank/training_data.shtml (because it was prepared before the tooling was available)
I am building a application where I am trying to use IBM Watson question & answer API.
Currently I see only corpus for Healthcare and Travel, but I would like to ingest Custom dataset suiting my needs. Can anyone please point me to right direction or exact API which does that or IBM already built explorer which I can use to upload the data files directly.
Thanks for the help
At this time you can not ingest corpus data into IBM Watson. That is coming in the future.