Hot answers tagged

3 votes

Performing a text classification based on a dictionary

As defined, there's no ML in this problem: the program would associate each keyword to a category, so it would consist of a loop over the words in the documents, and inside the loop there is an if ...
user avatar
  • 21.8k
1 vote
Accepted

What are some methods to reduce a dataframe so I can pass it as one sample to an SVM?

SVM are not meant to solve "arbitrarily long" classification problem, therefore you have few choices: use PCA for sequences, however it takes very long since it has to build a giant matrix ...
user avatar
1 vote

Model to implement Question Answering System over structured data

One efficient way is to use the roberta base squad 2 model, using your text as context and then ask questions. It should work well and the model can be downloaded directly. ...
user avatar
1 vote
Accepted

BertTokenizer Loading Problem

It could be due to an internet connection issue, that's why it is always safer to download your model in a local folder first and then load it directly using the absolute path. In addition to that ...
user avatar
1 vote

How to deal with spelling errors in NLP classfier (low resource language)

If the language doesn't have any spelling correction tool and you want to take care of spelling errors, practically you'd have to build one by using string similarity measures, and using frequency as ...
user avatar
  • 21.8k
1 vote

Manipulating noise to get some data in right format and apply it to task using PPO

From my understanding of your question, you are looking to implement a learning-to-sort algorithm. There are current learning-to-sort machine learning solutions that do not require reinforcement ...
user avatar
1 vote
Accepted

Manipulating noise to get some data in right format and apply it to task using PPO

In terms of process optimization, RL is an excellent option but the environment definition and its policy could be difficult to implement. That's why a genetic algorithm is a good alternative as it ...
user avatar
1 vote

LSTM basic doubt

First of all LSTM does not know the word it received, not at least in the sense that you think. LSTM like all neural net cell works with numeric vector representation. Even if you would build a ...
user avatar
  • 4,418
1 vote

NLP logistic regression

This is a completely plausible model. You have five features (probably one-hot encoded) and then a categorical outcome. This is a reasonable place to use a (multinomial) logistic regression. Depending ...
user avatar
  • 2,830

Only top scored, non community-wiki answers of a minimum length are eligible