Conditional set generation using Seq2seq models
Published in arXiv (Cornell University) • May 25, 2022
NobleIDNI0P33W98R78S43
Authors:,,
Aman Madaan
Dheeraj Rajagopal
Niket Tandon
Abstract
Conditional set generation learns a mapping from an input sequence of tokens to a set. Several NLP tasks, such as entity typing and dialogue emotion tagging, are instances of set generation. Seq2Seq models, a popular choice for set generation, treat a set as a sequence and do not fully leverage its ...
Finding related papers...
Discussions
(0)No comments yet
Be the first to share your thoughts!