Entity Linking Based on Sentence Representation
Entity linking involves mapping ambiguous mentions in documents to the correct entities in a given knowledge base. Most existing methods failed to link when a mention appears multiple times in a document, since the conflict of its contexts in different locations may lead to difficult linking. Senten...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2021/8895742 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832550545219387392 |
|---|---|
| author | Bingjing Jia Zhongli Wu Pengpeng Zhou Bin Wu |
| author_facet | Bingjing Jia Zhongli Wu Pengpeng Zhou Bin Wu |
| author_sort | Bingjing Jia |
| collection | DOAJ |
| description | Entity linking involves mapping ambiguous mentions in documents to the correct entities in a given knowledge base. Most existing methods failed to link when a mention appears multiple times in a document, since the conflict of its contexts in different locations may lead to difficult linking. Sentence representation, which has been studied based on deep learning approaches recently, can be used to resolve the above issue. In this paper, an effective entity linking model is proposed to capture the semantic meaning of the sentences and reduce the noise introduced by different contexts of the same mention in a document. This model first uses the symmetry of the Siamese network to learn the sentence similarity. Then, the attention mechanism is added to improve the interaction between input sentences. To show the effectiveness of our sentence representation model combined with attention mechanism, named ELSR, extensive experiments are conducted on two public datasets. Results illustrate that our model outperforms the baselines and achieves the superior performance. |
| format | Article |
| id | doaj-art-39bcbe1e330244d19e0321384f4e8c73 |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-39bcbe1e330244d19e0321384f4e8c732025-02-03T06:06:30ZengWileyComplexity1076-27871099-05262021-01-01202110.1155/2021/88957428895742Entity Linking Based on Sentence RepresentationBingjing Jia0Zhongli Wu1Pengpeng Zhou2Bin Wu3Beijing University of Posts and Telecommunications, Beijing 100876, ChinaAnhui Science and Technology University, Bengbu 233000, ChinaBeijing University of Posts and Telecommunications, Beijing 100876, ChinaBeijing University of Posts and Telecommunications, Beijing 100876, ChinaEntity linking involves mapping ambiguous mentions in documents to the correct entities in a given knowledge base. Most existing methods failed to link when a mention appears multiple times in a document, since the conflict of its contexts in different locations may lead to difficult linking. Sentence representation, which has been studied based on deep learning approaches recently, can be used to resolve the above issue. In this paper, an effective entity linking model is proposed to capture the semantic meaning of the sentences and reduce the noise introduced by different contexts of the same mention in a document. This model first uses the symmetry of the Siamese network to learn the sentence similarity. Then, the attention mechanism is added to improve the interaction between input sentences. To show the effectiveness of our sentence representation model combined with attention mechanism, named ELSR, extensive experiments are conducted on two public datasets. Results illustrate that our model outperforms the baselines and achieves the superior performance.http://dx.doi.org/10.1155/2021/8895742 |
| spellingShingle | Bingjing Jia Zhongli Wu Pengpeng Zhou Bin Wu Entity Linking Based on Sentence Representation Complexity |
| title | Entity Linking Based on Sentence Representation |
| title_full | Entity Linking Based on Sentence Representation |
| title_fullStr | Entity Linking Based on Sentence Representation |
| title_full_unstemmed | Entity Linking Based on Sentence Representation |
| title_short | Entity Linking Based on Sentence Representation |
| title_sort | entity linking based on sentence representation |
| url | http://dx.doi.org/10.1155/2021/8895742 |
| work_keys_str_mv | AT bingjingjia entitylinkingbasedonsentencerepresentation AT zhongliwu entitylinkingbasedonsentencerepresentation AT pengpengzhou entitylinkingbasedonsentencerepresentation AT binwu entitylinkingbasedonsentencerepresentation |