Are there some research papers about text-to-set generation?

Question

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!

Answer 1

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:

https://github.com/chenyuntc/PyTorchText