Focusing on Context is NICE: Improving Overshadowed Entity Disambiguation
Not on the map. Why?
Abstract (arXiv)
Entity disambiguation (ED) is the task of mapping an ambiguous entity mention to the corresponding entry in a structured knowledge base. Previous research showed that entity overshadowing is a significant challenge for existing ED models: when presented with an ambiguous entity mention, the models are much more likely to rank a more frequent yet less contextually relevant entity at the top. Here, we present NICE, an iterative approach that uses entity type information to leverage context and avoid over-relying on the frequency-based prior. Our experiments show that NICE achieves the best performance results on the overshadowed entities while still performing competitively on the frequent entities.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 8 of its 20 references that are in the map. First posted on arXiv 12 Oct 2022.
Builds on
8 of 20 references.
References · 8
- 2020Autoregressive Entity Retrievalcited by 333
- 2019A Survey on Recent Advances in Named Entity Recognition from Deep Learning modelscited by 117
- 2019Scalable Zero-shot Entity Linking with Dense Entity Retrievalcited by 85
- 2017Deep Joint Entity Disambiguation with Local Neural Attentioncited by 79
- 2020REL: An Entity Linker Standing on the Shoulders of Giantscited by 61
- 2018Improving Entity Linking by Modeling Latent Relations between Mentionscited by 53
- 2016Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguationcited by 48
- 2021Robustness Evaluation of Entity Disambiguation Using Prior Probes:the Case of Entity Overshadowingcited by 11
Built on by
Not cited yet.