Conditional set generation using Seq2seq models
Published in Underline Science Inc. • Nov 17, 2022
NobleIDNI7P35W49R38S73
Authors:,
Association for Computational Linguistics 2022
Aman Madaan
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 are a popular choice to model set generation but they treat a set as a sequence and do not ful...
Finding related papers...
Discussions
(0)No comments yet
Be the first to share your thoughts!