Classifying Relations by Ranking with Convolutional Neural Networks
C. Santos, B. Xiang, and B. Zhou. (2015)cite arxiv:1504.06580Comment: Accepted as a long paper in the 53rd Annual Meeting of the Association for Computational Linguistics (ACL 2015).
Abstract
Relation classification is an important semantic processing task for which
state-ofthe-art systems still rely on costly handcrafted features. In this work
we tackle the relation classification task using a convolutional neural network
that performs classification by ranking (CR-CNN). We propose a new pairwise
ranking loss function that makes it easy to reduce the impact of artificial
classes. We perform experiments using the the SemEval-2010 Task 8 dataset,
which is designed for the task of classifying the relationship between two
nominals marked in a sentence. Using CRCNN, we outperform the state-of-the-art
for this dataset and achieve a F1 of 84.1 without using any costly handcrafted
features. Additionally, our experimental results show that: (1) our approach is
more effective than CNN followed by a softmax classifier; (2) omitting the
representation of the artificial class Other improves both precision and
recall; and (3) using only word embeddings as input features is enough to
achieve state-of-the-art results if we consider only the text between the two
target nominals.
%0 Generic
%1 santos2015classifying
%A Santos, Cicero Nogueira dos
%A Xiang, Bing
%A Zhou, Bowen
%D 2015
%K cnn deep_learning relex
%T Classifying Relations by Ranking with Convolutional Neural Networks
%U http://arxiv.org/abs/1504.06580
%X Relation classification is an important semantic processing task for which
state-ofthe-art systems still rely on costly handcrafted features. In this work
we tackle the relation classification task using a convolutional neural network
that performs classification by ranking (CR-CNN). We propose a new pairwise
ranking loss function that makes it easy to reduce the impact of artificial
classes. We perform experiments using the the SemEval-2010 Task 8 dataset,
which is designed for the task of classifying the relationship between two
nominals marked in a sentence. Using CRCNN, we outperform the state-of-the-art
for this dataset and achieve a F1 of 84.1 without using any costly handcrafted
features. Additionally, our experimental results show that: (1) our approach is
more effective than CNN followed by a softmax classifier; (2) omitting the
representation of the artificial class Other improves both precision and
recall; and (3) using only word embeddings as input features is enough to
achieve state-of-the-art results if we consider only the text between the two
target nominals.
@misc{santos2015classifying,
abstract = {Relation classification is an important semantic processing task for which
state-ofthe-art systems still rely on costly handcrafted features. In this work
we tackle the relation classification task using a convolutional neural network
that performs classification by ranking (CR-CNN). We propose a new pairwise
ranking loss function that makes it easy to reduce the impact of artificial
classes. We perform experiments using the the SemEval-2010 Task 8 dataset,
which is designed for the task of classifying the relationship between two
nominals marked in a sentence. Using CRCNN, we outperform the state-of-the-art
for this dataset and achieve a F1 of 84.1 without using any costly handcrafted
features. Additionally, our experimental results show that: (1) our approach is
more effective than CNN followed by a softmax classifier; (2) omitting the
representation of the artificial class Other improves both precision and
recall; and (3) using only word embeddings as input features is enough to
achieve state-of-the-art results if we consider only the text between the two
target nominals.},
added-at = {2018-02-22T11:42:48.000+0100},
author = {Santos, Cicero Nogueira dos and Xiang, Bing and Zhou, Bowen},
biburl = {https://www.bibsonomy.org/bibtex/247b483da7676ca337f6be250bd408392/dallmann},
description = {1504.06580.pdf},
interhash = {a3f35abd3401ff73c584c053ff4e8201},
intrahash = {47b483da7676ca337f6be250bd408392},
keywords = {cnn deep_learning relex},
note = {cite arxiv:1504.06580Comment: Accepted as a long paper in the 53rd Annual Meeting of the Association for Computational Linguistics (ACL 2015)},
timestamp = {2018-02-22T11:42:48.000+0100},
title = {Classifying Relations by Ranking with Convolutional Neural Networks},
url = {http://arxiv.org/abs/1504.06580},
year = 2015
}