Abstract
The existence of external (“side”) semantic knowledge has been shown to result in more expressive computational event models. To enable the use of side information that may be noisy or missing, we propose a semi-supervised information bottleneck-based discrete latent variable model. We reparameterize the model’s discrete variables with auxiliary continuous latent variables and a light-weight hierarchical structure. Our model is learned to minimize the mutual information between the observed data and optional side knowledge that is not already captured by the new, auxiliary variables. We theoretically show that our approach generalizes past approaches, and perform an empirical case study of our approach on event modeling. We corroborate our theoretical results with strong empirical experiments, showing that the proposed method outperforms previous proposed approaches on multiple datasets.- Anthology ID:
- 2023.eacl-main.56
- Volume:
- Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
- Month:
- May
- Year:
- 2023
- Address:
- Dubrovnik, Croatia
- Editors:
- Andreas Vlachos, Isabelle Augenstein
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 797–814
- Language:
- URL:
- https://aclanthology.org/2023.eacl-main.56
- DOI:
- 10.18653/v1/2023.eacl-main.56
- Cite (ACL):
- Mehdi Rezaee and Francis Ferraro. 2023. RevUp: Revise and Update Information Bottleneck for Event Representation. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 797–814, Dubrovnik, Croatia. Association for Computational Linguistics.
- Cite (Informal):
- RevUp: Revise and Update Information Bottleneck for Event Representation (Rezaee & Ferraro, EACL 2023)
- PDF:
- https://preview.aclanthology.org/revert-3132-ingestion-checklist/2023.eacl-main.56.pdf