A game theoretic approach to class-wise selective rationalization
© 2019 Neural information processing systems foundation. All rights reserved. Selection of input features such as relevant pieces of text has become a common technique of highlighting how complex neural predictors operate. The selection can be optimized post-hoc for trained models or incorporated di...
Main Authors: | Chang, Shiyu, Zhang, Yang, Jaakkola, Tommi S |
---|---|
Other Authors: | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
Format: | Article |
Language: | English |
Published: |
2021
|
Online Access: | https://hdl.handle.net/1721.1/129379 |
Similar Items
-
A game theoretic approach to class-wise selective rationalization
by: Chang, Shiyu, et al.
Published: (2021) -
Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control
by: Yu, Mo, et al.
Published: (2021) -
Rationalizing Neural Predictions
by: Lei, Tao, et al.
Published: (2020) -
Local aggregative games
by: Jaakkola, Tommi, et al.
Published: (2021) -
Learning Tree Structured Potential Games
by: Garg, Vikas K., et al.
Published: (2021)