A Bidirectional Multi-paragraph Reading Model for Zero-shot Entity Linking

Authors

  • Hongyin Tang State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences University of Chinese Academy of Sciences, Beijing China
  • Xingwu Sun Meituan-Dianping Group, China
  • Beihong Jin State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences University of Chinese Academy of Sciences, Beijing China
  • Fuzheng Zhang Meituan-Dianping Group, China

Keywords:

Information Extraction

Abstract

Recently, a zero-shot entity linking task is introduced to challenge the generalization ability of entity linking models. In this task, mentions must be linked to unseen entities and only the textual information is available. In order to make full use of the documents, previous work has proposed a BERT-based model which can only take fixed length of text as input. However, the key information for entity linking may exist in nearly everywhere of the documents thus the proposed model cannot capture them all. To leverage more textual information and enhance text understanding capability, we propose a bidirectional multi-paragraph reading model for the zero-shot entity linking task. Firstly, the model treats the mention context as a query and matches it with multiple paragraphs of the entity description documents. Then, the mention-aware entity representation obtained from the first step is used as a query to match multiple paragraphs in the document containing the mention through an entity-mention attention mechanism. In particular, a new pre-training strategy is employed to strengthen the representative ability. Experimental results show that our bidirectional model can capture long-range context dependencies and outperform the baseline model by 3-4% in terms of accuracy.

Downloads

Published

2021-05-18

How to Cite

Tang, H., Sun, X., Jin, B., & Zhang, F. (2021). A Bidirectional Multi-paragraph Reading Model for Zero-shot Entity Linking. Proceedings of the AAAI Conference on Artificial Intelligence, 35(15), 13889-13897. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17636

Issue

Section

AAAI Technical Track on Speech and Natural Language Processing II