Multitopic Coherence Extraction for Global Entity Linking
Entity linking is a process of linking mentions in a document with entities in a knowledge base. Collective entity disambiguation refers to mapping of multiple mentions in a document with their corresponding entities in a knowledge base. Most previous research has been based on the assumption that a...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/21/3638 |
| _version_ | 1797468485951946752 |
|---|---|
| author | Chao Zhang Zhao Li Shiwei Wu Tong Chen Xiuhao Zhao |
| author_facet | Chao Zhang Zhao Li Shiwei Wu Tong Chen Xiuhao Zhao |
| author_sort | Chao Zhang |
| collection | DOAJ |
| description | Entity linking is a process of linking mentions in a document with entities in a knowledge base. Collective entity disambiguation refers to mapping of multiple mentions in a document with their corresponding entities in a knowledge base. Most previous research has been based on the assumption that all mentions in the same document represent the same topic. However, mentions usually correspond to different topics. In this article, we proposes a new global model to explore the extraction of multitopic coherence in the same document. Herein, we present mention association graphs and candidate entity association graphs to obtain multitopic coherence features of the same document using graph neural networks (GNNs). In particular, we propose a variant GNN for our model and a particular graph readout function. We conducted extensive experiments on several datasets to demonstrate the effectiveness to the proposed model. |
| first_indexed | 2024-03-09T19:07:12Z |
| format | Article |
| id | doaj.art-29a393d4c1614f9089f21993025cf009 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T19:07:12Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-29a393d4c1614f9089f21993025cf0092023-11-24T04:27:08ZengMDPI AGElectronics2079-92922022-11-011121363810.3390/electronics11213638Multitopic Coherence Extraction for Global Entity LinkingChao Zhang0Zhao Li1Shiwei Wu2Tong Chen3Xiuhao Zhao4School of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaSchool of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaEvay Info, Jinan 250101, ChinaEvay Info, Jinan 250101, ChinaSchool of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaEntity linking is a process of linking mentions in a document with entities in a knowledge base. Collective entity disambiguation refers to mapping of multiple mentions in a document with their corresponding entities in a knowledge base. Most previous research has been based on the assumption that all mentions in the same document represent the same topic. However, mentions usually correspond to different topics. In this article, we proposes a new global model to explore the extraction of multitopic coherence in the same document. Herein, we present mention association graphs and candidate entity association graphs to obtain multitopic coherence features of the same document using graph neural networks (GNNs). In particular, we propose a variant GNN for our model and a particular graph readout function. We conducted extensive experiments on several datasets to demonstrate the effectiveness to the proposed model.https://www.mdpi.com/2079-9292/11/21/3638entity linkinggraph neural networkgraph attention network |
| spellingShingle | Chao Zhang Zhao Li Shiwei Wu Tong Chen Xiuhao Zhao Multitopic Coherence Extraction for Global Entity Linking Electronics entity linking graph neural network graph attention network |
| title | Multitopic Coherence Extraction for Global Entity Linking |
| title_full | Multitopic Coherence Extraction for Global Entity Linking |
| title_fullStr | Multitopic Coherence Extraction for Global Entity Linking |
| title_full_unstemmed | Multitopic Coherence Extraction for Global Entity Linking |
| title_short | Multitopic Coherence Extraction for Global Entity Linking |
| title_sort | multitopic coherence extraction for global entity linking |
| topic | entity linking graph neural network graph attention network |
| url | https://www.mdpi.com/2079-9292/11/21/3638 |
| work_keys_str_mv | AT chaozhang multitopiccoherenceextractionforglobalentitylinking AT zhaoli multitopiccoherenceextractionforglobalentitylinking AT shiweiwu multitopiccoherenceextractionforglobalentitylinking AT tongchen multitopiccoherenceextractionforglobalentitylinking AT xiuhaozhao multitopiccoherenceextractionforglobalentitylinking |