Hansel: A Chinese Few-Shot and Zero-Shot Entity Linking Benchmark
Not on the map. Why?
Abstract (arXiv)
Modern Entity Linking (EL) systems entrench a popularity bias, yet 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. The test set of Hansel is human annotated and reviewed, created with a novel method for collecting zero-shot EL datasets. It covers 10K diverse documents in news, social media posts and other web articles, with Wikidata as its target Knowledge Base. We demonstrate that the existing state-of-the-art EL system performs poorly on Hansel (R@1 of 36.6% on Few-Shot). We then establish a strong baseline that scores a R@1 of 46.2% 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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 21 of its 49 references that are in the map. First posted on arXiv 26 Jul 2022.
Builds on
21 of 49 references.
References · 21
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
- 2020Autoregressive Entity Retrievalcited by 333
- 2019Zero-Shot Entity Linking by Reading Entity Descriptionscited by 124
- 2020Entities as Experts: Sparse Memory Access with Entity Supervisioncited by 100
- 2015LCSTS: A Large Scale Chinese Short Text Summarization Datasetcited by 65
- 2020REL: An Entity Linker Standing on the Shoulders of Giantscited by 61
- 2018Question Answering by Reasoning Across Documents with Graph Convolutional Networkscited by 56
- 2020Entity Linking in 100 Languagescited by 52
- 2021Multilingual Autoregressive Entity Linkingcited by 50
- 2018DeepType: Multilingual Entity Linking by Neural Type System Evolutioncited by 41
- 2021Evaluating Entity Disambiguation and the Role of Popularity in Retrieval-Based NLPcited by 30
9 more
- 2020Empirical Evaluation of Pretraining Strategies for Supervised Entity Linkingcited by 17
- 2017Neural Cross-Lingual Entity Linkingcited by 15
- 2020Learning Cross-Context Entity Representations from Textcited by 12
- 2021Robustness Evaluation of Entity Disambiguation Using Prior Probes:the Case of Entity Overshadowingcited by 11
- 2022TABi: Type-Aware Bi-Encoders for Open-Domain Entity Retrievalcited by 8
- 2018Joint Multilingual Supervision for Cross-lingual Entity Linkingcited by 7
- 2020Overview of the CCKS 2019 Knowledge Graph Evaluation Track: Entity, Relation, Event and QAcited by 6
- 2019Towards Zero-resource Cross-lingual Entity Linkingcited by 5
- 2014Feature Engineering for Knowledge Base Constructioncited by 3
Built on by
Citing papers per year: 2023: 2.
2 papers.