Abstract
Learning quality document embeddings is a fundamental problem in natural language processing (NLP), information retrieval (IR), recommendation systems, and search engines. Despite recent advances in the development of transformer-based models that produce sentence embeddings with self-contrastive learning, the encoding of long documents (Ks of words) is still challenging with respect to both efficiency and quality considerations. Therefore, we train Longfomer-based document encoders using a state-of-the-art unsupervised contrastive learning method (SimCSE). Further on, we complement the baseline method -siamese neural network- with additional convex neural networks based on functional Bregman divergence aiming to enhance the quality of the output document representations. We show that overall the combination of a self-contrastive siamese network and our proposed neural Bregman network outperforms the baselines in two linear classification settings on three long document topic classification tasks from the legal and biomedical domains.- Anthology ID:
- 2023.findings-acl.771
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2023
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 12181–12190
- Language:
- URL:
- https://aclanthology.org/2023.findings-acl.771
- DOI:
- 10.18653/v1/2023.findings-acl.771
- Cite (ACL):
- Daniel Saggau, Mina Rezaei, Bernd Bischl, and Ilias Chalkidis. 2023. Efficient Document Embeddings via Self-Contrastive Bregman Divergence Learning. In Findings of the Association for Computational Linguistics: ACL 2023, pages 12181–12190, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Efficient Document Embeddings via Self-Contrastive Bregman Divergence Learning (Saggau et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2023.findings-acl.771.pdf