2 papers
cs.IT2023
Elastic Information Bottleneck
Yuyan Ni, Yanyan Lan, Ao Liu +1
Information bottleneck is an information-theoretic principle of representation learning that aims to learn a maximally compressed representation that preserves as much information…
cs.CL2021
Improving Logical-Level Natural Language Generation with Topic-Conditioned Data Augmentation and Logical Form Generation
Ao Liu, Congjian Luo, Naoaki Okazaki
Logical Natural Language Generation, i.e., generating textual descriptions that can be logically entailed by a structured table, has been a challenge due to the low fidelity of the…