Imposing Relation Structure in Language-Model Embeddings Using Contrastive Learning
arXiv:2109.00840 · doi:10.18653/v1/2021.conll-1.27
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.
arXiv commentTo be presented at CoNLL 2021
References in corpus (8)
- Adam: A Method for Stochastic Optimization
- Semi-Supervised Classification with Graph Convolutional Networks
- A Simple Framework for Contrastive Learning of Visual Representations
- Data-Efficient Image Recognition with Contrastive Predictive Coding
- Joint entity recognition and relation extraction as a multi-head selection problem
- Contrastive Learning of Medical Visual Representations from Paired Images and Text
- Span-based Joint Entity and Relation Extraction with Transformer Pre-training
- Neural Metric Learning for Fast End-to-End Relation Extraction