MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity Representations

Xinyin Ma, Yong Jiang, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, Weiming Lu


Abstract
Entity retrieval, which aims at disambiguating mentions to canonical entities from massive KBs, is essential for many tasks in natural language processing. Recent progress in entity retrieval shows that the dual-encoder structure is a powerful and efficient framework to nominate candidates if entities are only identified by descriptions. However, they ignore the property that meanings of entity mentions diverge in different contexts and are related to various portions of descriptions, which are treated equally in previous works. In this work, we propose Multi-View Entity Representations (MuVER), a novel approach for entity retrieval that constructs multi-view representations for entity descriptions and approximates the optimal view for mentions via a heuristic searching method. Our method achieves the state-of-the-art performance on ZESHEL and improves the quality of candidates on three standard Entity Linking datasets.
Anthology ID:
2021.emnlp-main.205
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2617–2624
Language:
URL:
https://aclanthology.org/2021.emnlp-main.205
DOI:
10.18653/v1/2021.emnlp-main.205
Bibkey:
Cite (ACL):
Xinyin Ma, Yong Jiang, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, and Weiming Lu. 2021. MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity Representations. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2617–2624, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity Representations (Ma et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.205.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.205.mp4
Code
 alibaba-nlp/muver
Data
ZESHEL