Entity and Evidence Guided Relation Extraction for DocRED

08/27/2020
by   Kevin Huang, et al.
0

Document-level relation extraction is a challenging task which requires reasoning over multiple sentences in order to predict relations in a document. In this paper, we pro-pose a joint training frameworkE2GRE(Entity and Evidence Guided Relation Extraction)for this task. First, we introduce entity-guided sequences as inputs to a pre-trained language model (e.g. BERT, RoBERTa). These entity-guided sequences help a pre-trained language model (LM) to focus on areas of the document related to the entity. Secondly, we guide the fine-tuning of the pre-trained language model by using its internal attention probabilities as additional features for evidence prediction.Our new approach encourages the pre-trained language model to focus on the entities and supporting/evidence sentences. We evaluate our E2GRE approach on DocRED, a recently released large-scale dataset for relation extraction. Our approach is able to achieve state-of-the-art results on the public leaderboard across all metrics, showing that our E2GRE is both effective and synergistic on relation extraction and evidence prediction.

READ FULL TEXT

page 4

page 8

12/18/2020

An Empirical Study of Using Pre-trained BERT Models for Vietnamese Relation Extraction Task at VLSP 2020

In this paper, we present an empirical study of using pre-trained BERT m...
09/26/2019

Fine-tune Bert for DocRED with Two-step Process

Modelling relations between multiple entities has attracted increasing a...
04/08/2020

Downstream Model Design of Pre-trained Language Model for Relation Extraction Task

Supervised relation extraction methods based on deep neural network play...
05/31/2020

Benchmarking BioRelEx for Entity Tagging and Relation Extraction

Extracting relationships and interactions between different biological e...
05/20/2019

Enriching Pre-trained Language Model with Entity Information for Relation Classification

Relation classification is an important NLP task to extract relations be...
02/04/2019

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

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