ETH-DS3Lab at SemEval-2018 Task 7: Effectively Combining Recurrent and Convolutional Neural Networks for Relation Classification and Extraction

by   Jonathan Rotsztejn, et al.
ETH Zurich

Reliably detecting relevant relations between entities in unstructured text is a valuable resource for knowledge extraction, which is why it has awaken significant interest in the field of Natural Language Processing. In this paper, we present a system for relation classification and extraction based on an ensemble of convolutional and recurrent neural networks that ranked first in 3 out of the 4 subtasks at SemEval 2018 Task 7. We provide detailed explanations and grounds for the design choices behind the most relevant features and analyze their importance.


page 1

page 2

page 3

page 4


Combining Recurrent and Convolutional Neural Networks for Relation Classification

This paper investigates two different neural architectures for the task ...

Big Green at WNUT 2020 Shared Task-1: Relation Extraction as Contextualized Sequence Classification

Relation and event extraction is an important task in natural language p...

Improved Relation Classification by Deep Recurrent Neural Networks with Data Augmentation

Nowadays, neural networks play an important role in the task of relation...

Combining Neural Networks and Log-linear Models to Improve Relation Extraction

The last decade has witnessed the success of the traditional feature-bas...

Structure Regularized Bidirectional Recurrent Convolutional Neural Network for Relation Classification

Relation classification is an important semantic processing task in the ...

Identifying Spatial Relations in Images using Convolutional Neural Networks

Traditional approaches to building a large scale knowledge graph have us...

Please sign up or login with your details

Forgot password? Click here to reset