I know that you can log metrics as your experiment progresses. For example the training loss over epochs for your DL model.
I was wondering if it was possible to do something similar for text. In my particular case I have a text model that generates some example text after each epoch and I wish to see what it's like. For example:
Epoch 1:
tHi is RubisH
Epoch 2:
Ok look slight better
Epoch 3:
I can speak English better than William Shakespeare
The workaround I can think of is to log this to a text file and push that as an artifact in mlflow. Was wondering if there was something else more native to mlflow.
You can use log_param/log_params for that. For long texts maybe it's better to use log_text instead...
Related
I'm using GPT-3 for some experiments where I prompt the language model with tests from cognitive science. The tests have the form of short text snippets. Now I'd like to check whether GPT-3 has already encountered these text snippets during training. Hence my question: Is there any way to sift through GPT-3's training text corpora? Can one find out whether a certain string is part of these text corpora?
Thanks for your help!
I don't think that's possible, unfortunately. GPT-3's training corpora is private.
But if that was possible, it would be great for detecting plagiarism. Maybe ask if it it knows where a certain line of text came from?
Here is the code:
finetuned_model = hub.load(hub_url)
shared_embedding_layer = hub.KerasLayer(finetuned_model,trainable=True)
"Fine Tune Network"
model.fit([left_inputs,right_inputs],similiarity,epochs=1,callbacks=[stopAtLossValue()])
The network looks like this.
After each epoch completes, my finetuned_model is updated slightly. What I would like to do is ideally two things:
Use this finetuned_model after each epoch
Save this finetuned_model after each epoch
This is interesting as I'm not actually interested in saving the model that is training. Is there are a way for me to do this?
Disclaimer: I'm not all that experience in Deep Learning
I want to train and use an ML based personal voice to text converter for a highly impaired voice, for a small set of 300-400 words. This is to be used for people with voice impairment. But cannot be generic because each person will have a unique voice input for words, depending on their type of impairment.
Wanted to know if there are any ML engines which allow for such a training. If not, what is the best approach to go about it.
Thanks
Most of the speech recognition engines support training (wav2letter, deepspeech, espnet, kaldi, etc), you just need to feed in the data. The only issue is that you need a lot of data to train reliably (1000 of samples for each word). You can check Google Commands dataset for example of how to train from scratch.
Since the training dataset will be pretty small for your case and will consist of just a few samples, you can probably start with existing pretrained model and finetune it on your samples to get best accuracy. You need to look on "few short learning" setups.
You can probably look on wav2vec 2.0 pretrained model, it should be effective for such learning. You can find examples and commands for fine-tuning and inference here.
You can also try fine-tuning Japser models in Google Commands for NVIDIA NEMO. It might be a little less effective but could still work and should be easier to setup.
I highely recommend watching the youtube original series "The age of AI"'s First season, episode two.
Basically, google already done this for people who can't really form normal words with impared voice. It is very interesting and speaks a little bit about how they done and doing that with ML technologies.
enter link description here
Could I ask about Stanford NER?? Actually, I'm trying to train my own model, to use it later for learning. According to the documentation, I have to add my own features in SeqClassifierFlags and add code for each Feature in NERFeatureFactory.
My questions is that, I have my tokens with all features extracted and Last column represents the label. So, is there any way in Stanford NER to give it my Tab-Delimeted file which contains 30 columns (1 is word , 28 are featurs, and 1 is label) to train my own model without spending time for extracting features???
Of course, in Testing phase, I will give it a file like the the aforementioned file without label to predict the label.
Is this possible or Not??
Many thanks in Advance
As explained in the FAQ page, the only way to customize the NER model is by inserting the data and specifying the features that you want to extract.
But, wait ... you have the data, and you have managed to extract the features, so I think you don't need the NER model, you need a classifier. I know this answer is pretty pretty late, but maybe this classifier will be a good place to start.
I am trying to do a timeline detection problem using text classification. As a newbie I am confused as to how I can go about with this. Is this a classification problem? i.e, Can I use the years(timelines) as outcomes and solve this as a classification problem?
You should be able to solve this as a classification problem as you suggest. An option could be to find or build a corpus consisting of texts tagged with the period in which they're set, and train a classification algorithm on this data set.
Another option could be to train a word space model on such a data set, and generate vectors for different periods of time (e.g. the 50s, 60s etc.). You could then create a document vector for the text you wish to classify, and find which of these time vectors yields the best match.
Might not work, but it could be interesting to see what results you get.
Hope this helps!