Relation Classification via Recurrent Neural Network with Attention and Tensor Layers
Relation classification is a crucial component in many Natural Language Processing (NLP) systems. In this paper, we propose a novel bidirectional recurrent neural network architecture (using Long Short-Term Memory, LSTM, cells) for relation classification, with an attention layer for organizing the...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tsinghua University Press
2018-09-01
|
| Series: | Big Data Mining and Analytics |
| Subjects: | |
| Online Access: | https://www.sciopen.com/article/10.26599/BDMA.2018.9020022 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832568974874771456 |
|---|---|
| author | Runyan Zhang Fanrong Meng Yong Zhou Bing Liu |
| author_facet | Runyan Zhang Fanrong Meng Yong Zhou Bing Liu |
| author_sort | Runyan Zhang |
| collection | DOAJ |
| description | Relation classification is a crucial component in many Natural Language Processing (NLP) systems. In this paper, we propose a novel bidirectional recurrent neural network architecture (using Long Short-Term Memory, LSTM, cells) for relation classification, with an attention layer for organizing the context information on the word level and a tensor layer for detecting complex connections between two entities. The above two feature extraction operations are based on the LSTM networks and use their outputs. Our model allows end-to-end learning from the raw sentences in the dataset, without trimming or reconstructing them. Experiments on the SemEval-2010 Task 8 dataset show that our model outperforms most state-of-the-art methods. |
| format | Article |
| id | doaj-art-4a0b15e4172e4012850a410c01e90f23 |
| institution | Kabale University |
| issn | 2096-0654 |
| language | English |
| publishDate | 2018-09-01 |
| publisher | Tsinghua University Press |
| record_format | Article |
| series | Big Data Mining and Analytics |
| spelling | doaj-art-4a0b15e4172e4012850a410c01e90f232025-02-02T23:47:25ZengTsinghua University PressBig Data Mining and Analytics2096-06542018-09-011323424410.26599/BDMA.2018.9020022Relation Classification via Recurrent Neural Network with Attention and Tensor LayersRunyan Zhang0Fanrong Meng1Yong Zhou2Bing Liu3<institution>China University of Mining and Technology</institution>, <city>Xuzhou</city> <postal-code>210009</postal-code>, <country>China</country>.<institution>China University of Mining and Technology</institution>, <city>Xuzhou</city> <postal-code>210009</postal-code>, <country>China</country>.<institution>China University of Mining and Technology</institution>, <city>Xuzhou</city> <postal-code>210009</postal-code>, <country>China</country>.<institution>China University of Mining and Technology</institution>, <city>Xuzhou</city> <postal-code>210009</postal-code>, <country>China</country>.Relation classification is a crucial component in many Natural Language Processing (NLP) systems. In this paper, we propose a novel bidirectional recurrent neural network architecture (using Long Short-Term Memory, LSTM, cells) for relation classification, with an attention layer for organizing the context information on the word level and a tensor layer for detecting complex connections between two entities. The above two feature extraction operations are based on the LSTM networks and use their outputs. Our model allows end-to-end learning from the raw sentences in the dataset, without trimming or reconstructing them. Experiments on the SemEval-2010 Task 8 dataset show that our model outperforms most state-of-the-art methods.https://www.sciopen.com/article/10.26599/BDMA.2018.9020022semantic relation classificationbidirectional recurrent neural network (rnns)attention mechanismneural tensor networks |
| spellingShingle | Runyan Zhang Fanrong Meng Yong Zhou Bing Liu Relation Classification via Recurrent Neural Network with Attention and Tensor Layers Big Data Mining and Analytics semantic relation classification bidirectional recurrent neural network (rnns) attention mechanism neural tensor networks |
| title | Relation Classification via Recurrent Neural Network with Attention and Tensor Layers |
| title_full | Relation Classification via Recurrent Neural Network with Attention and Tensor Layers |
| title_fullStr | Relation Classification via Recurrent Neural Network with Attention and Tensor Layers |
| title_full_unstemmed | Relation Classification via Recurrent Neural Network with Attention and Tensor Layers |
| title_short | Relation Classification via Recurrent Neural Network with Attention and Tensor Layers |
| title_sort | relation classification via recurrent neural network with attention and tensor layers |
| topic | semantic relation classification bidirectional recurrent neural network (rnns) attention mechanism neural tensor networks |
| url | https://www.sciopen.com/article/10.26599/BDMA.2018.9020022 |
| work_keys_str_mv | AT runyanzhang relationclassificationviarecurrentneuralnetworkwithattentionandtensorlayers AT fanrongmeng relationclassificationviarecurrentneuralnetworkwithattentionandtensorlayers AT yongzhou relationclassificationviarecurrentneuralnetworkwithattentionandtensorlayers AT bingliu relationclassificationviarecurrentneuralnetworkwithattentionandtensorlayers |