ETH-DS3Lab at SemEval-2018 Task 7: Effectively Combining Recurrent and
Convolutional Neural Networks for Relation Classification and Extraction
J. Rotsztejn, N. Hollenstein, and C. Zhang. (2018)cite arxiv:1804.02042Comment: Accepted to SemEval 2018 (12th International Workshop on Semantic Evaluation).
Abstract
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.
Description
ETH-DS3Lab at SemEval-2018 Task 7: Effectively Combining Recurrent and
Convolutional Neural Networks for Relation Classification and Extraction
%0 Generic
%1 rotsztejn2018ethds3lab
%A Rotsztejn, Jonathan
%A Hollenstein, Nora
%A Zhang, Ce
%D 2018
%K 2018 classification cnn ecl eth extraction network neural nlp nn relation rnn semeval semeval18
%T ETH-DS3Lab at SemEval-2018 Task 7: Effectively Combining Recurrent and
Convolutional Neural Networks for Relation Classification and Extraction
%U http://arxiv.org/abs/1804.02042
%X 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.
@misc{rotsztejn2018ethds3lab,
abstract = {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.},
added-at = {2018-04-25T14:12:39.000+0200},
author = {Rotsztejn, Jonathan and Hollenstein, Nora and Zhang, Ce},
biburl = {https://www.bibsonomy.org/bibtex/2fea6a0fe18346ae85807bd2cd2ee3608/schwemmlein},
description = {ETH-DS3Lab at SemEval-2018 Task 7: Effectively Combining Recurrent and
Convolutional Neural Networks for Relation Classification and Extraction},
interhash = {488e4b6acaf6eed8ae153b99fce2af42},
intrahash = {fea6a0fe18346ae85807bd2cd2ee3608},
keywords = {2018 classification cnn ecl eth extraction network neural nlp nn relation rnn semeval semeval18},
note = {cite arxiv:1804.02042Comment: Accepted to SemEval 2018 (12th International Workshop on Semantic Evaluation)},
timestamp = {2018-09-13T10:33:34.000+0200},
title = {ETH-DS3Lab at SemEval-2018 Task 7: Effectively Combining Recurrent and
Convolutional Neural Networks for Relation Classification and Extraction},
url = {http://arxiv.org/abs/1804.02042},
year = 2018
}