Imposing Relation Structure in Language-Model Embeddings Using Contrastive Learning
This addresses the problem of improving relation extraction in NLP for researchers and practitioners, offering a novel method that is incremental in enhancing existing embedding techniques.
The paper tackles the limitation of language model embeddings in capturing high-level semantic information like entity relations by proposing a contrastive learning framework that imposes graph-based relation structure on sentence embeddings, achieving state-of-the-art results on relation extraction with a simple KNN classifier.
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.