1
$\begingroup$

lets say I have three texts:

  1. "make a heading that says hello word"
  2. "make a heading of hello world"
  3. "create heading consist of hello world"

How can I fetch those groups of words using AI which is referring to heading i.e hello world in this case. Which AI frameworks or libraries can do that?

in all examples heading is pointing to hello world (which i am referring as group of words). so basically i want those words which will be a part of heading or in other word there is a relationship between them. another example i can give is "I am watching Breaking bad" so there is a relationship between watching and breaking bad and i want to extract what are you watching.

What's the best approach? Do I have to train a model for that or there are some other techniques that can get it done?

$\endgroup$
6
  • 1
    $\begingroup$ Please explain more clearly. What does 'fetch those groups of words' mean? You already have words. Why do you want more words? What is it you are hoping AI is going to do for you? $\endgroup$ Jan 13 at 13:49
  • 1
    $\begingroup$ in all examples heading is pointing to hello world (which i am referring as group of words). so basically i want those words which will be a part of heading or in other word there is a relationship between them. another example i can give is "I am watching Breaking bad" so there is a relationship between watching and breaking bad and i want to extract what are you watching. I hope I have made myself more clear. thanks for taking your time out. $\endgroup$
    – ukasha
    Jan 13 at 15:47
  • $\begingroup$ Hello @ukasha, could you update your question to include the details that you just provided - this may help you to get more answers $\endgroup$
    – mark mark
    Jan 13 at 16:01
  • 1
    $\begingroup$ hi @markmark thanks. i have added. $\endgroup$
    – ukasha
    Jan 13 at 16:43
  • $\begingroup$ Spacy is a machine learning library to (among others) analyze linguistic dependency and offers solutions for Named Entity Recognition (i.e. finding names or titles like "Breaking Bad" which refer to some entity). You can either use pretrained models or train your own models. So, this library might offer what you are looking for. $\endgroup$
    – Daniel B.
    Jan 14 at 1:47
0
$\begingroup$

I think U are looking for PLSA for PLSA either U find out those topics(catogeries) with EM or NNMF Personally I recommend NNMF or u can use LDA which is Bayesian version of PLSA

here is code for PLSA: https://github.com/Man-ash/Probabilistic-Latent-semantic-analysis which use NNMF

for EM method I code it by myself but i am not sure if it is right https://stackoverflow.com/questions/65783880/problem-about-m-step-in-probabilistic-latent-semantic-analysis-with-code

$\endgroup$
0
$\begingroup$

You can also pose your problem as co-reference resolution. Try Huggingface's neuralcoref library.

$\endgroup$
1
  • $\begingroup$ I've noticed that you have provided many shorts answers. Sometimes, an answer doesn't have to be longer than 1-2 lines, but that's rarely the case. Note that I'm not saying that long answers are better. In fact, very long answers are also not good. I've seen so many answers that were bad only because they were so long and didn't focus on answering the question. So, please, before providing another answer, take a look at ai.stackexchange.com/help/how-to-answer. So, in this case, you could at least provide a link to what you're suggesting the OP to look into. $\endgroup$
    – nbro
    Feb 20 at 17:53

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.