Cognitive Information Bottleneck: Extracting Minimal Sufficient Cognitive Language Processing Signals

Yuto Harada, Yohei Oseki


Abstract
In Reinforcement Learning from Human Feedback (RLHF), explicit human feedback, such as rankings, is employed to align Natural Language Processing (NLP) models with human preferences. In contrast, the potential of implicit human feedback, encompassing cognitive processing signals like eye-tracking and brain activity, remains underexplored. These signals capture unconscious human responses but are often marred by noise and redundancy, complicating their application to specific tasks. To address this issue, we introduce the Cognitive Information Bottleneck (CIB), a method that extracts only the task-relevant information from cognitive processing signals. Grounded in the principles of the information bottleneck, CIB aims to learn representations that maximize the mutual information between the representations and targets while minimizing the mutual information between inputs and representations. By employing CIB to filter out redundant information from cognitive processing signals, our goal is to provide representations that are both minimal and sufficient. This approach enables more efficient fitting of models to inputs. Our results show that the proposed method outperforms existing methods in efficiently compressing various cognitive processing signals and significantly enhances performance on downstream tasks. Evaluated on public datasets, our model surpasses contemporary state-of-the-art models. Furthermore, by analyzing these compressed representations, we offer insights into how cognitive processing signals can be leveraged to improve performance.
Anthology ID:
2024.lrec-main.309
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
3480–3489
Language:
URL:
https://aclanthology.org/2024.lrec-main.309
DOI:
Bibkey:
Cite (ACL):
Yuto Harada and Yohei Oseki. 2024. Cognitive Information Bottleneck: Extracting Minimal Sufficient Cognitive Language Processing Signals. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 3480–3489, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Cognitive Information Bottleneck: Extracting Minimal Sufficient Cognitive Language Processing Signals (Harada & Oseki, LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-main.309.pdf