Hansel: A Chinese Few-Shot and Zero-Shot Entity Linking Benchmark

Anonymous

Abstract: Modern Entity Linking (EL) systems entrench a popularity bias. However, there is no dataset focusing on tail and emerging entities in languages other than English. We present Hansel, a new benchmark in Chinese that fills the vacancy of non-English few-shot and zero-shot EL challenges. Hansel is human annotated and reviewed, with a novel method for collecting zero-shot EL datasets. It is a diverse dataset covering 8.2K documents in news, social media posts and other web articles, with Wikidata as its target Knowledge Base. We demonstrate that existing state-of-the-art EL system performs poorly on Hansel (R@1 of 35.8% on Few-Shot). We then establish a strong baseline that scores a R@1 of 43.2% on Few-Shot and 76.6% on Zero-Shot on our dataset. We also show that our baseline achieves competitive results on TAC-KBP2015 Chinese Entity Linking task.