A Read-and-Select Framework for Zero-shot Entity Linking
This addresses entity linking for unseen entities, improving generalization with a simpler approach compared to previous multi-phase pre-training methods.
The paper tackles zero-shot entity linking by proposing a read-and-select framework that models mention-entity matching and cross-entity comparison, achieving a state-of-the-art performance with a 2.55% micro-average accuracy gain on the ZESHEL dataset.
Zero-shot entity linking (EL) aims at aligning entity mentions to unseen entities to challenge the generalization ability. Previous methods largely focus on the candidate retrieval stage and ignore the essential candidate ranking stage, which disambiguates among entities and makes the final linking prediction. In this paper, we propose a read-and-select (ReS) framework by modeling the main components of entity disambiguation, i.e., mention-entity matching and cross-entity comparison. First, for each candidate, the reading module leverages mention context to output mention-aware entity representations, enabling mention-entity matching. Then, in the selecting module, we frame the choice of candidates as a sequence labeling problem, and all candidate representations are fused together to enable cross-entity comparison. Our method achieves the state-of-the-art performance on the established zero-shot EL dataset ZESHEL with a 2.55% micro-average accuracy gain, with no need for laborious multi-phase pre-training used in most of the previous work, showing the effectiveness of both mention-entity and cross-entity interaction.