Extracting chemical-protein relations using attention-based neural networks.

Extracting chemical-protein relations using attention-based neural networks.
复制标题

DOI:
10.1093/database/bay102
复制
发表时间:
2018-01-01
期刊:
Database : the journal of biological databases and curation
影响因子:
--
通讯作者:
Liu H
Liu H
中科院分区:
其他
文献类型:
--
作者:
Liu S;Shen F;Komandur Elayavilli R;Wang Y;Rastegar-Mojarad M;Chaudhary V;Liu H

文献摘要

参考文献

被引文献

相似文献

关系提取是自然语言处理领域的一项重要任务。在本文中,我们描述了我们对BioCreative VI任务5的方法:文本挖掘化学-蛋白质相互作用。我们研究了多种深度神经网络(DNN)模型,包括卷积神经网络、循环神经网络(RNNs)和基于注意的(ATT-) RNNs (ATT-RNNs)来提取化学-蛋白质关系。我们的实验结果表明,在不使用注意力的情况下,ATT-RNN模型的表现优于同类模型,并且在测试的dnn中,att门控循环单元(ATT-GRU)在测试集中的微平均F1得分为0.527,表现最佳。此外,词级注意权值的结果也表明,当使用语义关系标签训练时,注意机制可以有效地选择最重要的触发词,而不需要语义解析和特征工程。该工作的源代码可从https://github.com/ohnlp/att-chemprot获得。
Relation extraction is an important task in the field of natural language processing. In this paper, we describe our approach for the BioCreative VI Task 5: text mining chemical–protein interactions. We investigate multiple deep neural network (DNN) models, including convolutional neural networks, recurrent neural networks (RNNs) and attention-based (ATT-) RNNs (ATT-RNNs) to extract chemical–protein relations. Our experimental results indicate that ATT-RNN models outperform the same models without using attention and the ATT-gated recurrent unit (ATT-GRU) achieves the best performing micro average F1 score of 0.527 on the test set among the tested DNNs. In addition, the result of word-level attention weights also shows that attention mechanism is effective on selecting the most important trigger words when trained with semantic relation labels without the need of semantic parsing and feature engineering. The source code of this work is available at https://github.com/ohnlp/att-chemprot.
通过卷积神经网络提取药物相互作用
DOI: 10.1155/2016/6918381
发表时间: 2016
影响因子: --
作者:
Liu S;Tang B;Chen Q;Wang X
通讯作者: Wang X
DOI: 10.1162/coli.2006.32.4.485
发表时间: 2006-12-01
影响因子: 9.3
作者:
Kiss, Tibor;Strunk, Jan
通讯作者: Strunk, Jan
DOI: 10.1186/s13326-015-0044-y
发表时间: 2016-04-29
影响因子: 1.9
作者:
Gupta S;Ross KE;Tudor CO;Wu CH;Schmidt CJ;Vijay-Shanker K
通讯作者: Vijay-Shanker K
通过卷积神经网络提取化学引起的疾病关系
DOI: 10.1093/database/bax024
发表时间: 2017-01-01
期刊: Database : the journal of biological databases and curation
影响因子: --
作者:
Gu J;Sun F;Qian L;Zhou G
通讯作者: Zhou G
DOI: 10.1186/1751-0473-9-1
发表时间: 2014-01-08
影响因子: --
作者:
Campos D;Bui QC;Matos S;Oliveira JL
通讯作者: Oliveira JL