Log In Sign Up

Improving Distantly-Supervised Relation Extraction through BERT-based Label Instance Embeddings

by   Despina Christou, et al.

Distantly-supervised relation extraction (RE) is an effective method to scale RE to large corpora but suffers from noisy labels. Existing approaches try to alleviate noise through multi-instance learning and by providing additional information, but manage to recognize mainly the top frequent relations, neglecting those in the long-tail. We propose REDSandT (Relation Extraction with Distant Supervision and Transformers), a novel distantly-supervised transformer-based RE method, that manages to capture a wider set of relations through highly informative instance and label embeddings for RE, by exploiting BERT's pre-trained model, and the relationship between labels and entities, respectively. We guide REDSandT to focus solely on relational tokens by fine-tuning BERT on a structured input, including the sub-tree connecting an entity pair and the entities' types. Using the extracted informative vectors, we shape label embeddings, which we also use as attention mechanism over instances to further reduce noise. Finally, we represent sentences by concatenating relation and instance embeddings. Experiments in the NYT-10 dataset show that REDSandT captures a broader set of relations with higher confidence, achieving state-of-the-art AUC (0.424).


page 1

page 2

page 3

page 4


Fine-tuning Pre-Trained Transformer Language Models to Distantly Supervised Relation Extraction

Distantly supervised relation extraction is widely used to extract relat...

A Simple, Strong and Robust Baseline for Distantly Supervised Relation Extraction

Distantly supervised relation extraction (DS-RE) is generally framed as ...

A Sample-Based Training Method for Distantly Supervised Relation Extraction with Pre-Trained Transformers

Multiple instance learning (MIL) has become the standard learning paradi...

Noise Mitigation for Neural Entity Typing and Relation Extraction

In this paper, we address two different types of noise in information ex...

Deep Bidirectional Transformers for Relation Extraction without Supervision

We present a novel framework to deal with relation extraction tasks in c...

Extracting Multiple-Relations in One-Pass with Pre-Trained Transformers

Most approaches to extraction multiple relations from a paragraph requir...