Bidirectional End-to-End Learning of Retriever-Reader Paradigm for Entity Linking
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909142818488320 |
|---|---|
| author | Li, Yinghui Jiang, Yong Li, Yangning Lu, Xingyu Xie, Pengjun Shen, Ying Zheng, Hai-Tao |
| author_facet | Li, Yinghui Jiang, Yong Li, Yangning Lu, Xingyu Xie, Pengjun Shen, Ying Zheng, Hai-Tao |
| contents | Entity Linking (EL) is a fundamental task for Information Extraction and Knowledge Graphs. The general form of EL (i.e., end-to-end EL) aims to first find mentions in the given input document and then link the mentions to corresponding entities in a specific knowledge base. Recently, the paradigm of retriever-reader promotes the progress of end-to-end EL, benefiting from the advantages of dense entity retrieval and machine reading comprehension. However, the existing study only trains the retriever and the reader separately in a pipeline manner, which ignores the benefit that the interaction between the retriever and the reader can bring to the task. To advance the retriever-reader paradigm to perform more perfectly on end-to-end EL, we propose BEER$^2$, a Bidirectional End-to-End training framework for Retriever and Reader. Through our designed bidirectional end-to-end training, BEER$^2$ guides the retriever and the reader to learn from each other, make progress together, and ultimately improve EL performance. Extensive experiments on benchmarks of multiple domains demonstrate the effectiveness of our proposed BEER$^2$. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_12245 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Bidirectional End-to-End Learning of Retriever-Reader Paradigm for Entity Linking Li, Yinghui Jiang, Yong Li, Yangning Lu, Xingyu Xie, Pengjun Shen, Ying Zheng, Hai-Tao Computation and Language Entity Linking (EL) is a fundamental task for Information Extraction and Knowledge Graphs. The general form of EL (i.e., end-to-end EL) aims to first find mentions in the given input document and then link the mentions to corresponding entities in a specific knowledge base. Recently, the paradigm of retriever-reader promotes the progress of end-to-end EL, benefiting from the advantages of dense entity retrieval and machine reading comprehension. However, the existing study only trains the retriever and the reader separately in a pipeline manner, which ignores the benefit that the interaction between the retriever and the reader can bring to the task. To advance the retriever-reader paradigm to perform more perfectly on end-to-end EL, we propose BEER$^2$, a Bidirectional End-to-End training framework for Retriever and Reader. Through our designed bidirectional end-to-end training, BEER$^2$ guides the retriever and the reader to learn from each other, make progress together, and ultimately improve EL performance. Extensive experiments on benchmarks of multiple domains demonstrate the effectiveness of our proposed BEER$^2$. |
| title | Bidirectional End-to-End Learning of Retriever-Reader Paradigm for Entity Linking |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2306.12245 |