Status Update
Comments
nr...@google.com <nr...@google.com>
nr...@google.com <nr...@google.com> #2
mo...@gtempaccount.com <mo...@gtempaccount.com> #3
Project id: restaurant-phone-reservat-b9tt
Location: us-east1
Please have a look, this is a blocker for us.
Thank you!
mo...@gtempaccount.com <mo...@gtempaccount.com> #4
Do we have an estimated time when these bugs will be solved, please?
nr...@google.com <nr...@google.com> #5
Hello,
Thank you for reaching out to us with your request.
We have duly noted your feedback and will thoroughly validate it. While we cannot provide an estimated time of implementation or guarantee the fulfillment of the issue, please be assured that your input is highly valued. Your feedback enables us to enhance our products and services.
We appreciate your continued trust and support in improving our Google Cloud Platform products. In case you want to report a new issue, please do not hesitate to create a new issue on the
Once again, we sincerely appreciate your valuable feedback; Thank you for your understanding and collaboration.
mo...@gtempaccount.com <mo...@gtempaccount.com> #6
Or can I follow up issue in this chat is it confidential?
mo...@gtempaccount.com <mo...@gtempaccount.com> #7
nr...@google.com <nr...@google.com> #8
Hello,
Can you check the issue link titled [Confidential] Dialogflow Entity Extraction Issue in Assigned to me
option on the left pane of the Buganizer.
Please don't hesitate to reach back if you face any issues.
de...@gmail.com <de...@gmail.com> #9
This issue was created on Dec 1st, but my first encounter dates back to the last week of november
In that issue people have posted the console log showcasing the probable source of the problem
A workaround has been published by users which "kinda works" but if you refresh the page you have to do it all over again
Moreover, in order to apply the workaround you have to break one of the most common sense best practices for keeping you safe from bad actors..
It's not a problem since you just need to read a couple of lines to understand that it's not dangerous, but not everybody on Dialogflow has the competences to actually know it just from reading the code
Honestly I'm surprised that such a bug has not been fixed yet
But I also wonder if there are ANY users who are not experiencing it
nr...@google.com <nr...@google.com> #10
Hello,
Thank you for reaching out to us with your request.
We have duly noted your feedback and will thoroughly validate it. While we cannot provide an estimated time of implementation or guarantee the fulfillment of the issue, please be assured that your input is highly valued. Your feedback enables us to enhance our products and services.
We appreciate your continued trust and support in improving our Google Cloud Platform products. In case you want to report a new issue, Please do not hesitate to create a new issue on the
Once again, we sincerely appreciate your valuable feedback; Thank you for your understanding and collaboration.
Description
I’ve entered the below phrases in the console to test recognition of our custom mns_store entity, and I’ve noticed that it only seems to recognise the entity when an exact phrase is used / the phrase exists within the training data of an intent. When using a similar but not exact phrase, the entity is no longer recognised and extracted. For example:
we’ve identified an extraction issue with our custom food_to_order entity ie.
This entity (food_to_order ) only contains 5 values (food,dinner,lunch,meal,catering). For some reason though, the words ‘order’ and ‘Christmas’ are being recognised by DF as values within this entity and are therefore being automatically labelled as such when adding new phrases.
We can remove and select the appropriate entity when adding phrases, however, as DF believes ‘order’ and ‘Christmas’ are a match, this entity is still being inappropriately extracted from customer utterances and is sometimes causing them to map to incorrect intents.
We understand this can sometimes happen due to user error when phrases are labelled incorrectly, but I’m confident this is not the problem here, as the training data has been checked and no issues are being flagged within the Validation.
Please refer the images for more details.
Please check into the issue and let us know if anything require from our end.