BERT fine-tuning for Conversational AI - nlp

I am trying to build a conversational AI chatbot. Since BERT is quite a popular model, I am thinking about using it. I can see that BERT has a pre-trained model for the Question Answering task. Can anyone tell me which version of the BERT model should I use to build a conversation AI? Or Can anyone direct me to the useful resources?
Thanks in advance!

Related

Alternative to Support Vector Machine for Intent Classification

I am trying to implement a chatbot using linked data. In a paper, I read that I can use SVM for the intent classification which is basically the first stage in conversational systems. It is the process of mapping queries to a predefined class. I wanted to know whether there is any other way or applications / programs that I can use to do this. Could someone please advise me?
Thank you in advance.
Rasa is an open-source platform that can be used to easily set up a chatbot, and through it you can set up several kinds of intent classification (including with an SVM).
It also allows you to annotate example utterances and map them to intents within the tool itself.
These tasks are certainly doable on your own, but if speed and easy integration with a working chatbot are priorities, then I recommend using a platform like that.

DNN network architecture of the original parent network from which the Intel OpenVINO pre-trained models were optimized and if yes, how?

I have used pre-trained models from OpenVINO for inference. I would like to know how to see the network structure of these models? And if I want to re-train these networks from scratch, can I know from which parent models these pre-trained models were originally derived from?
Information about Intel pre-trained models is available at the following page, “Overview of OpenVINO™ Toolkit Intel's Pre-Trained Models”.
https://docs.openvinotoolkit.org/2020.4/omz_models_intel_index.html
Information about public pre-trained models is available at the following page, “Overview of OpenVINO™ Toolkit Public Models”.
https://docs.openvinotoolkit.org/2020.4/omz_models_public_index.html
DL Workbench can be used to visualize the network structure. DL Workbench is a web-based graphical environment that enables users to visualize, fine-tune, and compare performance of deep learning models. More information about DL Workbench is available at the following page, “Introduction to Deep Learning Workbench”.
https://docs.openvinotoolkit.org/2020.4/workbench_docs_Workbench_DG_Introduction.html

Custom Vision save curent model

i'm using Custom vision from Microsoft service to classify image. Since the model will have to be re train few times a years, I would like to know if I can save current version of azure custom vision model to re train my new model on the same version? because I guess microsoft will try to increase performances of its service among time so model used on this tools will probably change...
You can export the model after each run, but you cannot use an existing model as a starting point for another training run.
So yes, as it is a managed service, Microsoft might optimize or somehow change the algorithms to train in the background. It is on you to decide if that works for you. If not, a managed service like this is probably generally not something you should use, but instead train your own models entirely.

Google Cloud API sentiment analysis

I was going through Google Cloud API for sentiment analysis. The thing which is not clear to me is that on what basis the sentiment scores and magnitudes are assigned? Is there any kind of lexicon or any kind of training data? Is there any algorithm which can clarify how sentiment score is assigned?
I work in Cloud Natural Language team at Google. What's mentioned in the above comment is correct. We have built models internally (neural nets) and exposing them via the API basically.

Manage scikit-learn model in Google Cloud Platform

We are trying to figure out how to host and run many of our existing scikit-learn and R models (as is) in GCP. It seems ML Engine is pretty specific to Tensorflow. How can I train a scikit-learn model on Google cloud platform and manage my model if the dataset is too large to pull into datalab? Can I still use ML Engine or is there a different approach most people take?
As an update I was able to get the python script that trains the scikit-learn model to run by submitting it as a training job to ML Engine but haven't found a way to host the pickled model or use it for prediction.
Cloud ML Engine only supports models written in TensorFlow.
If you're using scikit-learn you might want to look at some of the higher level TensorFlow libraries like TF Learn or Keras. They might help migrate your model to TensorFlow in which case you could then use Cloud ML Engine.
It's possible, Cloud ML has this feature from Dec 2017, As of today it is provided as an early access. Basically Cloud ML team is testing this feature but you can also be part of it. More on here.
Use the following command to deploy your scikit-learn models to cloud ml. Please note these parameters may change in future.
gcloud ml-engine versions create ${MODEL_VERSION} --model=${MODEL} --origin="gs://${MODEL_PATH_IN_BUCKET}" --runtime-version="1.2" --framework="SCIKIT_LEARN"
sklearn is now supported on ML Engine.
Here is a fully worked out example of using fully-managed scikit-learn training, online prediction and hyperparameter tuning:
https://github.com/GoogleCloudPlatform/training-data-analyst/blob/master/blogs/sklearn/babyweight_skl.ipynb

Resources