Relation Extraction using Explicit Context Conditioning

Abstract

Relation Extraction (RE) aims to label relations between groups of marked entities in raw text. Most current RE models learn context-aware representations of the target entities that are then used to establish relation between them. This works well for intra-sentence RE and we call them first-order relations. However, this methodology can sometimes fail to capture complex and long dependencies. To address this, we hypothesize that at times two target entities can be explicitly connected via a context token. We refer to such indirect relations as second-order relations and describe an efficient implementation for computing them. These second-order relation scores are then combined with first-order relation scores. Our empirical results show that the proposed method leads to state-of-the-art performance over two biomedical datasets.

Accepted for Publication at NAACL 2019

References in corpus (5)

• Convolutional Sequence to Sequence Learning
• A Survey of Deep Learning Methods for Relation Extraction
• Improving Hospital Mortality Prediction with Medical Named Entities and Multimodal Learning
• Joint Entity Extraction and Assertion Detection for Clinical Text
• A hybrid deep learning approach for medical relation extraction

Cited by in corpus (2)

• Assessment of Amazon Comprehend Medical: Medication Information Extraction
• Towards User Friendly Medication Mapping Using Entity-Boosted Two-Tower Neural Network