Zero-shot Entity Linking with Efficient Long Range Sequence Modeling

Zonghai Yao, Liangliang Cao, Huapu Pan


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
Bibkey:
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)
Copy Citation:
PDF:
https://aclanthology.org/2020.findings-emnlp.228.pdf
Code
 seasonyao/Zero-Shot-Entity-Linking