Hey, Recently the folks at PolyAI have open-sourced a new sentence encoding model called ConveRT which is pretrained on a large conversational dataset and hence claims better conversational representations over traditional large language models like BERT, etc. The idea resonates very well with what we also believe and have been working on internally at Rasa. Since they open sourced their model as a TFHub model , we decided to build a quick featurizer based on this to extract representations and use them with downstream intent classification models already existing inside Rasa. In our internal tests, the model does give a significant boost to intent classification accuracy on multiple datasets. We would love the community to try it out and share evaluation numbers on their test sets. We have released the featurizer as part of Rasa 1.5.0. You can try by doing a pip install of Rasa- pip install rasa==1.5.0 The featurizer uses an optional dependency tensorflow_text. Install it with - pip install --no-deps tensorflow_text==1.15.1 Now you are ready to use the ConveRTFeaturizer . In the project directory, we recommend using a config along these lines - language: en pipeline: - name: WhitespaceTokenizer - name: ConveRTFeaturizer - name: EmbeddingIntentClassifier This uses the ConveRT model as a feature extractor alone and we do not fine tune it along with our intent classifier. Please note that this model can only be used for a dataset in english language. Feel free to change the config params of EmbeddingIntentClassifier according to your dataset. It would be great if you can share the numbers for evaluation metrics on your test dataset here.

@arbazkhan971 Share your VM detail and cloud provider name. Before upgrading pip, please run sudo apt-get update if you are using ubuntu

Account (Plan: Free) Version 2.3.35 Region United States (us) Web Interface http://127.0.0.1:4040 Forwarding http://86ce8c8d.ngrok.io -> http://localhost:80 Forwarding https://86ce8c8d.ngrok.io -> http://localhost:80 Connections ttl opn rt1 rt5 p50 p90 0 0 0.00 0.00 0.00 0.00

Hey, you need to use ngrok tcp 22 as a command and ensure, that ssh is running. As an alternative, we could use TeamViewer or something else. Regards

Hi, julian.gerhard@susiandjames.com Regards

Is it possible to persist the conveRT model instead of downloading the model on fly during training?

@DivyashaAgrawal The ConveRT model is downloaded from TFHub for the first time it is run on any new machine. It is persisted in TFhub’s own cache for retrieving it the next time it is run. So the next time time training or inferencing is run on the same machine, it won’t be downloaded but just retrieved from the cache.

Hi @arbazkhan971 Are you still facing any issue with TF installation? If yes, I would suggest opening a new thread on the forum to discuss about it since it’s a much more narrower topic and may not pertain to everyone on the thread. Feel free to post the link of the thread here if you wish to. Thanks

Hey @BahlingerTh Thank you for bringing this to our attention, we have adjusted the tracking settings for the announcement section so that it will only notify the community for the first announcement, and no longer notify for every response. If you would like to make further adjustments to your personal settings, you can do this by clicking on the tracking circle in the top right of each topic page or going to ‘notifications’ in your user profile settings. [image]

Feedback on ConveRT Model + Rasa NLU

Rasa Open Source

BahlingerTh (Thomas Bahlinger) December 2, 2019, 7:23am 49

Sorry, but does this stuff really belong to “Announcements” and should it be broadcasted via E-Mail?

Topic		Replies	Views
Trouble using ConveRTFeaturizer Rasa Open Source	3	872	October 17, 2021
ConveRT has been taken down Rasa Open Source	2	613	September 30, 2020
ConveRTFeaturizer model URL Rasa Open Source	0	312	March 4, 2022
Rasa nlu train never ends while using ConveRTTokenizer in the pipeline Rasa Open Source	0	583	April 26, 2020
How to use ConveRT Featurizer in Windows Rasa Open Source	8	1067	June 8, 2022

Feedback on ConveRT Model + Rasa NLU

Related topics