Augmenting BERT-style Models with Predictive Coding to Improve Discourse-level Representations
Vladimir Araujo, Andrés Villa, Marcelo Mendoza, Marie-Francine Moens, Alvaro Soto
Abstract
Current language models are usually trained using a self-supervised scheme, where the main focus is learning representations at the word or sentence level. However, there has been limited progress in generating useful discourse-level representations. In this work, we propose to use ideas from predictive coding theory to augment BERT-style language models with a mechanism that allows them to learn suitable discourse-level representations. As a result, our proposed approach is able to predict future sentences using explicit top-down connections that operate at the intermediate layers of the network. By experimenting with benchmarks designed to evaluate discourse-related knowledge using pre-trained sentence representations, we demonstrate that our approach improves performance in 6 out of 11 tasks by excelling in discourse relationship detection.- Anthology ID:
- 2021.emnlp-main.240
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3016–3022
- Language:
- URL:
- https://aclanthology.org/2021.emnlp-main.240
- DOI:
- 10.18653/v1/2021.emnlp-main.240
- Cite (ACL):
- Vladimir Araujo, Andrés Villa, Marcelo Mendoza, Marie-Francine Moens, and Alvaro Soto. 2021. Augmenting BERT-style Models with Predictive Coding to Improve Discourse-level Representations. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 3016–3022, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Augmenting BERT-style Models with Predictive Coding to Improve Discourse-level Representations (Araujo et al., EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2021.emnlp-main.240.pdf