I have googled but find no results.

Text-to-(word)set generation or sequence-to-(token)set generation.

For example, input a text and then output the tags for this text:

'Peter is studying English' --> {'good behavior','person','doing something'}

Thank you!

  • 1
    $\begingroup$ This sounds as either 1) a funky text summarization problem or 2) a multi-class classification problem (where you just don't have a dataset for it yet). $\endgroup$ – Bruno Lubascher Dec 10 '19 at 18:30
  • $\begingroup$ Also can consider semantic parsing methods. $\endgroup$ – DunkOnly Dec 26 '19 at 7:21

Check out these papers below and google keywords: Multi-label Classification.

X-BERT: eXtreme Multi-label Text Classification with BERT
HAXMLNet: Hierarchical Attention Network for Extreme Multi-Label Text Classification
SGM: Sequence Generation Model for Multi-label Classification
Ranking-Based Autoencoder for Extreme Multi-label Classification
AttentionXML: Label Tree-based Attention-Aware Deep Model for High-Performance Extreme Multi-Label Text Classification

Also check out the code below:



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.