Improving Few-shot and Zero-shot Entity Linking with Coarse-to-Fine Lexicon-based Retriever

TL;DR

This paper introduces a two-layer coarse-to-fine lexicon-based retrieval method for few-shot and zero-shot entity linking, significantly improving candidate retrieval accuracy without extensive fine-tuning.

Contribution

It proposes a novel coarse-to-fine lexicon-based retriever that effectively narrows down entity candidates using entity names and descriptions, enhancing zero-shot and few-shot linking.

Findings

Achieved top performance in NLPCC 2023 Shared Task 6

Outperformed existing methods in Chinese few-shot and zero-shot entity linking

Effective disambiguation of tail and emerging entities

Abstract

Few-shot and zero-shot entity linking focus on the tail and emerging entities, which are more challenging but closer to real-world scenarios. The mainstream method is the ''retrieve and rerank'' two-stage framework. In this paper, we propose a coarse-to-fine lexicon-based retriever to retrieve entity candidates in an effective manner, which operates in two layers. The first layer retrieves coarse-grained candidates by leveraging entity names, while the second layer narrows down the search to fine-grained candidates within the coarse-grained ones. In addition, this second layer utilizes entity descriptions to effectively disambiguate tail or new entities that share names with existing popular entities. Experimental results indicate that our approach can obtain superior performance without requiring extensive finetuning in the retrieval stage. Notably, our approach ranks the 1st in NLPCC 2023 Shared Task 6 on Chinese Few-shot and Zero-shot Entity Linking.