Imposing Relation Structure in Language-Model Embeddings Using Contrastive Learning
Christos Theodoropoulos, James Henderson, Andrei Catalin Coman, Marie-Francine Moens
Abstract
Though language model text embeddings have revolutionized NLP research, their ability to capture high-level semantic information, such as relations between entities in text, is limited. In this paper, we propose a novel contrastive learning framework that trains sentence embeddings to encode the relations in a graph structure. Given a sentence (unstructured text) and its graph, we use contrastive learning to impose relation-related structure on the token level representations of the sentence obtained with a CharacterBERT (El Boukkouri et al., 2020) model. The resulting relation-aware sentence embeddings achieve state-of-the-art results on the relation extraction task using only a simple KNN classifier, thereby demonstrating the success of the proposed method. Additional visualization by a tSNE analysis shows the effectiveness of the learned representation space compared to baselines. Furthermore, we show that we can learn a different space for named entity recognition, again using a contrastive learning objective, and demonstrate how to successfully combine both representation spaces in an entity-relation task.- Anthology ID:
- 2021.conll-1.27
- Volume:
- Proceedings of the 25th Conference on Computational Natural Language Learning
- Month:
- November
- Year:
- 2021
- Address:
- Online
- Editors:
- Arianna Bisazza, Omri Abend
- Venue:
- CoNLL
- SIG:
- SIGNLL
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 337–348
- Language:
- URL:
- https://aclanthology.org/2021.conll-1.27
- DOI:
- 10.18653/v1/2021.conll-1.27
- Cite (ACL):
- Christos Theodoropoulos, James Henderson, Andrei Catalin Coman, and Marie-Francine Moens. 2021. Imposing Relation Structure in Language-Model Embeddings Using Contrastive Learning. In Proceedings of the 25th Conference on Computational Natural Language Learning, pages 337–348, Online. Association for Computational Linguistics.
- Cite (Informal):
- Imposing Relation Structure in Language-Model Embeddings Using Contrastive Learning (Theodoropoulos et al., CoNLL 2021)
- PDF:
- https://preview.aclanthology.org/naacl-24-ws-corrections/2021.conll-1.27.pdf
- Code
- christos42/CLDR_CLNER_models
- Data
- Adverse Drug Events (ADE) Corpus