Supervised Response Selector [Experimental] - Announcements / Release Announcements - Rasa Community Forum
👋 Introducing the Rasa Playground
Supervised Response Selector [Experimental]
post by dakshvar22 on Jul 30, 2019
We have been working on a new exciting feature which includes two new components - retrieval actions and supervised response selector. Checkout the introduction to the feature, give it a go and share your feedback with us on the overall feature idea, possible use cases you envision, ease of integration and any other suggestions you may have.
post by JiteshGaikwad on Oct 7, 2019
hi @dakshvar22, Thanks for the the feature, it was easy to handle the small talk and interruptions without writing stories for each small talk within the stories. Below are few things which I would like to share
I am using the latest Rasa(1.3.7) and Rasa - X(0.21.3) version this is how my nlu.md fine looks like:
and it responds properly for the small talk:
but the problem occurs when I test it in Rasa X, I dont see any response from the bot
pic_51302×595 17.4 KB](https://europe1.discourse-cdn.com/flex013/uploads/rasa/original/2X/f/f6b614799d0053782ec498d21310ef33921aa990.png "pic_5")
post by dakshvar22 on Oct 7, 2019
@JiteshGaikwad Thanks for writing about the problem in detail. Yes, Rasa X / Interactive learning do not support Retrieval Actions as of now, since the feature is experimental and we want to gather substantial feedback before fully integrating it with the complete stack.
post by dakshvar22 on Oct 7, 2019
@JiteshGaikwad Completely agree with your suggestion. Will be added in the docs in the next patch release. Thanks
post by dakshvar22 on Oct 7, 2019
Regarding the first part of the problem, where you mentioned that the reply from the bot is not displayed: I tested with same versions of Rasa and Rasa-X and it works on my side. Here is what I did:
- Created a rasa project using
rasa init - Added some retrieval actions and retrieval intents.
- Trained the bot using
rasa train - Started Rasa X with
rasa x - Tested an example conversation and retrieval action gets triggered with correct bot message getting displayed.
Did you do anything different?
post by thusithaC on Oct 9, 2019
Hi @dakshvar22. Any updates about the longer term functionality of the feature? i.e. Will it be taken away or radically changed in the near future? I have a bot I’d like to try this feature to see if there is a performance upgrade over the current but hesitant to do so given the experimental nature of the feature and the amount of code changes I have to do.
post by dakshvar22 on Oct 9, 2019
@thusithaC Thanks for your question. We are currently collecting feedback on the training data format for retrieval actions because we are not completely sure of it at this moment. So, once we have that, we’ll make a decision on the next steps for the feature.
post by thusithaC on Oct 14, 2019
Thanks for the answer @dakshvar22. Understanding the logic was indeed helpful. I have one more question about data-cleaning we would like to perform before passing on text to a ML component. i.e. the response text we would like the user to see might have to be cleaned a bit to make it more suitable for training the ResponseSelector component.
post by dakshvar22 on Oct 15, 2019
@thusithaC Yes, the response text is stored as response attribute within the Message object inside NLU pipeline. So, train and process method of your custom component can basically act on them and perform any cleaning that’s needed.
post by neelkes on Oct 16, 2019
Hi @dakshvar22 I’m trying out the ResponseSelector and need some help to get going.
post by neelkes on Oct 17, 2019
The issue was not with my setup but with non-ASCII spaces in the responses.md file.
post by thusithaC on Oct 24, 2019
Thanks @dakshvar22. So far so good. There are a couple of new issues.
post by sten on Oct 26, 2019
I’m about to test it …
post by mjspeck on Oct 29, 2019
In your responses.md file are you able to have multi-line text responses, including bullet points?
post by dakshvar22 on Oct 31, 2019
@mjspeck No, currently we only support plain text.
post by mjspeck on Nov 4, 2019
Is there any way to use the fallback policy with the supervised response selector, similar to how it’s used with a normal intent classifier? Would be useful if the chatbot is not confident about which FAQ is being asked.
post by dakshvar22 on Nov 5, 2019
@mjspeck That could be a good addition, although we haven’t thought of developing it yet.
post by Nick_Kazakov on Nov 6, 2019
I encountered the same error “Cannot train a classifier. Need at least 2 different classes”.
post by dakshvar22 on Nov 8, 2019
Yes, integration of response selector with Rasa X is in progress. We’ll let you know once it is fully integrated.
post by Nick_Kazakov on Nov 11, 2019
Also, I can’t use response selection with default_ask_affirmation.
post by dakshvar22 on Nov 26, 2019
Not yet. But that’s a good point. We’ll give this a thought. Thanks.
post by tocosastalo on Dec 4, 2019
Hello, and what if I need to run story depending on what specific intent was identified.
post by ShayVD on Dec 5, 2019
Is there a way to execute “respond_chitchat” from a custom action?
post by dakshvar22 on Dec 6, 2019
It isn’t possible as of now, but will give more thought to it how it should be incorporated. Thanks.
post by kavan on Dec 18, 2019
This is a great step towards handling single-turn interactions separately. However, I have a few questions based on how I was using the traditional approach and how using response retrieval models would change it.
post by saurabh-m523 on Dec 25, 2019
I think a fallback policy for response selector would be a really nice feature.
post by madstuntman on Jan 15, 2020
Hi @dakshvar22! Do you continue on Rasa X and response retrieval integration? Thanks!
post by dakshvar22 on Jan 21, 2020
Hi @madstuntman, it is definitely on the roadmap but no release date has been set yet.
post by rasafan on Feb 3, 2020
Has anyone developed an FAQ bot with this option that is actually being used on their website or somewhere else?
post by rasafan on Feb 4, 2020
I’ve followed the article and implemented everything and get this error:
post by JiteshGaikwad on Feb 4, 2020
Hey @rasafan, you have not written the responses properly in responses.md file.
post by regel on Feb 17, 2020
I definitely need the feature in Rasa X too. +1
post by teresalazar13 on Mar 25, 2020
Can response actions have custom information (besides “text”), just like normal messages?
post by solyarisoftware on Apr 22, 2020
I have the same request.
post by ZordoC on May 20, 2020
Hey! Can I use a custom action as a response selector response?
post by dingusagar on Oct 5, 2020
What type of model does response selector use. Is it a simple feed forward network with the sparse and dense features as input?
post by petasis on Oct 9, 2020
@dingusagar I am not an expert, but from what I understand, the response selector is based on DIET, which uses a transformer.