Text-Classification | Implementation of papers for text classification | Machine Learning library

This my script:

I am looking at an implementation of RCNN for text classification using PyTorch. Full Code. There are two points where the dimensions of tensors are permuted using the permute function. The first is after the LSTM layer and before tanh. The second is after a linear layer and before a max pooling layer.

Could you please explain why the permutation is necessary or useful?

Relevant Code

I have a dataset with paragraphs that I need to classify into two classes. These paragraphs are usually 3-5 sentences long. The overwhelming majority of them are less than 500 words long. I would like to make use of BERT to tackle this problem.

I am wondering how I should use BERT to generate vector representations of these paragraphs and especially, whether it is fine to just pass the whole paragraph into BERT?

There have been informative discussions of related problems here and here. These discussions focus on how to use BERT for representing whole documents. In my case the paragraphs are not that long, and indeed could be passed to BERT without exceeding its maximum length of 512. However, BERT was trained on sentences. Sentences are relatively self-contained units of meaning. I wonder if feeding multiple sentences into BERT doesn't conflict fundamentally with what the model was designed to do (although this appears to be done regularly).

I'm getting an unusual high accuracy on a sentiment analysis classifier I'm testing with python sklearn library. This is usually some sort of training data leakage but I can't figure out if that's the case.

My dataset has ~50k nonduplicated IMDB reviews.

I am building a text classification model for imdb sentiment analysis dataset. I downloaded the dataset and followed the tutorial given here - https://developers.google.com/machine-learning/guides/text-classification/step-4

The error I get is

This issue has been posted a handful of times in SO, but I still can't figure out what is the problem with my code, especially because it comes from a tutorial in medium and the author makes the code available on google colab

I have seen other users having problem with wrong variable types #56304986 (which is not my case, as my model input is the output of tokenizer) and even seen the function I am trying to use (tf.data.Dataset.from_tensor_slices) being suggested as a solution #56304986.

The line yielding error is:

I am a beginner at this,

I have a classification problem and my data looks like below:

and so on...

Result column is dependent variable. None of the data is Ordinal. (Name column is having 36 different names.)

As it is categorical data i tried OneHotEncoding and i got ValueError: Number of features of the model must match the input

Which i understood and referred this : SO Question and it got fixed.

Also there was another site : Medium to solve this ValueError by using Pandas factorize function.

My Question is:

1. what is the correct way to approach this? Should i factorize and apply OneHotEncoding ?
2. or Since my data is not Ordinal i shouldn't use factorize?
3. I am always getting 100% accuracy. Is it because of the encoding i do ?

My code below:

Training

I'm playing with a multiclass classification problem and for fun I wanted to try different models. I found a blog that used LSTM for classification and was trying to adjust my model to work.

Here is my model:

I've been trying to find a suitable model for my project (multiclass German text classification) but got a little confused with the models offered here. There are models with text-classification tag, but they are for binary classification. Most of the other models are for [MASK] word predicting. I am not sure, which one to choose and if it will work with multiple classes at all

Would appreciate any advice!