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.
BibTeX
@inproceedings{ma-etal-2021-muver,
title = "{M}u{VER}: {I}mproving First-Stage Entity Retrieval with Multi-View Entity Representations",
author = "Ma, Xinyin and
Jiang, Yong and
Bach, Nguyen and
Wang, Tao and
Huang, Zhongqiang and
Huang, Fei and
Lu, Weiming",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.205/",
doi = "10.18653/v1/2021.emnlp-main.205",
pages = "2617--2624"
}