Deep Entity Linking via Eliminating Semantic Ambiguity With BERT
Entity linking refers to the task of aligning mentions of entities in the text to their corresponding entries in a specific knowledge base, which is of great significance for many natural language process applications such as semantic text understanding and knowledge fusion. The pivotal of this prob...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8911323/ |
| _version_ | 1818855493223841792 |
|---|---|
| author | Xiaoyao Yin Yangchen Huang Bin Zhou Aiping Li Long Lan Yan Jia |
| author_facet | Xiaoyao Yin Yangchen Huang Bin Zhou Aiping Li Long Lan Yan Jia |
| author_sort | Xiaoyao Yin |
| collection | DOAJ |
| description | Entity linking refers to the task of aligning mentions of entities in the text to their corresponding entries in a specific knowledge base, which is of great significance for many natural language process applications such as semantic text understanding and knowledge fusion. The pivotal of this problem is how to make effective use of contextual information to disambiguate mentions. Moreover, it has been observed that, in most cases, mention has similar or even identical strings to the entity it refers to. To prevent the model from linking mentions to entities with similar strings rather than the semantically similar ones, in this paper, we introduce the advanced language representation model called BERT (Bidirectional Encoder Representations from Transformers) and design a hard negative samples mining strategy to fine-tune it accordingly. Based on the learned features, we obtain the valid entity through computing the similarity between the textual clues of mentions and the entity candidates in the knowledge base. The proposed hard negative samples mining strategy benefits entity linking from the larger, more expressive pre-trained representations of BERT with limited training time and computing sources. To the best of our knowledge, we are the first to equip entity linking task with the powerful pre-trained general language model by deliberately tackling its potential shortcoming of learning literally, and the experiments on the standard benchmark datasets show that the proposed model yields state-of-the-art results. |
| first_indexed | 2024-12-19T08:09:29Z |
| format | Article |
| id | doaj.art-d64b5790b7b447bb8b4e74090c5d8ce3 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-19T08:09:29Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-d64b5790b7b447bb8b4e74090c5d8ce32022-12-21T20:29:40ZengIEEEIEEE Access2169-35362019-01-01716943416944510.1109/ACCESS.2019.29554988911323Deep Entity Linking via Eliminating Semantic Ambiguity With BERTXiaoyao Yin0https://orcid.org/0000-0002-8207-2512Yangchen Huang1https://orcid.org/0000-0002-2273-3649Bin Zhou2Aiping Li3Long Lan4https://orcid.org/0000-0002-4238-8985Yan Jia5College of Computer, National University of Defense Technology, Changsha, ChinaCollege of Computer, National University of Defense Technology, Changsha, ChinaCollege of Computer, National University of Defense Technology, Changsha, ChinaCollege of Computer, National University of Defense Technology, Changsha, ChinaCollege of Computer, National University of Defense Technology, Changsha, ChinaCollege of Computer, National University of Defense Technology, Changsha, ChinaEntity linking refers to the task of aligning mentions of entities in the text to their corresponding entries in a specific knowledge base, which is of great significance for many natural language process applications such as semantic text understanding and knowledge fusion. The pivotal of this problem is how to make effective use of contextual information to disambiguate mentions. Moreover, it has been observed that, in most cases, mention has similar or even identical strings to the entity it refers to. To prevent the model from linking mentions to entities with similar strings rather than the semantically similar ones, in this paper, we introduce the advanced language representation model called BERT (Bidirectional Encoder Representations from Transformers) and design a hard negative samples mining strategy to fine-tune it accordingly. Based on the learned features, we obtain the valid entity through computing the similarity between the textual clues of mentions and the entity candidates in the knowledge base. The proposed hard negative samples mining strategy benefits entity linking from the larger, more expressive pre-trained representations of BERT with limited training time and computing sources. To the best of our knowledge, we are the first to equip entity linking task with the powerful pre-trained general language model by deliberately tackling its potential shortcoming of learning literally, and the experiments on the standard benchmark datasets show that the proposed model yields state-of-the-art results.https://ieeexplore.ieee.org/document/8911323/Entity linkingnatural language processing (NLP)bidirectional encoder representations from transformers (BERT)deep neural network (DNN) |
| spellingShingle | Xiaoyao Yin Yangchen Huang Bin Zhou Aiping Li Long Lan Yan Jia Deep Entity Linking via Eliminating Semantic Ambiguity With BERT IEEE Access Entity linking natural language processing (NLP) bidirectional encoder representations from transformers (BERT) deep neural network (DNN) |
| title | Deep Entity Linking via Eliminating Semantic Ambiguity With BERT |
| title_full | Deep Entity Linking via Eliminating Semantic Ambiguity With BERT |
| title_fullStr | Deep Entity Linking via Eliminating Semantic Ambiguity With BERT |
| title_full_unstemmed | Deep Entity Linking via Eliminating Semantic Ambiguity With BERT |
| title_short | Deep Entity Linking via Eliminating Semantic Ambiguity With BERT |
| title_sort | deep entity linking via eliminating semantic ambiguity with bert |
| topic | Entity linking natural language processing (NLP) bidirectional encoder representations from transformers (BERT) deep neural network (DNN) |
| url | https://ieeexplore.ieee.org/document/8911323/ |
| work_keys_str_mv | AT xiaoyaoyin deepentitylinkingviaeliminatingsemanticambiguitywithbert AT yangchenhuang deepentitylinkingviaeliminatingsemanticambiguitywithbert AT binzhou deepentitylinkingviaeliminatingsemanticambiguitywithbert AT aipingli deepentitylinkingviaeliminatingsemanticambiguitywithbert AT longlan deepentitylinkingviaeliminatingsemanticambiguitywithbert AT yanjia deepentitylinkingviaeliminatingsemanticambiguitywithbert |