Abstract
This paper considers the problem of zero-shot entity linking, in which a link in the test time may not present in training. Following the prevailing BERT-based research efforts, we find a simple yet effective way is to expand the long-range sequence modeling. Unlike many previous methods, our method does not require expensive pre-training of BERT with long position embeddings. Instead, we propose an efficient position embeddings initialization method called Embedding-repeat, which initializes larger position embeddings based on BERT-Base. On the zero-shot entity linking dataset, our method improves the STOA from 76.06% to 79.08%, and for its long data, the corresponding improvement is from 74.57% to 82.14%. Our experiments suggest the effectiveness of long-range sequence modeling without retraining the BERT model.- Anthology ID:
- 2020.findings-emnlp.228
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2020
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Editors:
- Trevor Cohn, Yulan He, Yang Liu
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2517–2522
- Language:
- URL:
- https://aclanthology.org/2020.findings-emnlp.228
- DOI:
- 10.18653/v1/2020.findings-emnlp.228
- Cite (ACL):
- Zonghai Yao, Liangliang Cao, and Huapu Pan. 2020. Zero-shot Entity Linking with Efficient Long Range Sequence Modeling. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2517–2522, Online. Association for Computational Linguistics.
- Cite (Informal):
- Zero-shot Entity Linking with Efficient Long Range Sequence Modeling (Yao et al., Findings 2020)
- PDF:
- https://preview.aclanthology.org/landing_page/2020.findings-emnlp.228.pdf
- Code
- seasonyao/Zero-Shot-Entity-Linking