MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity Representations
This work addresses entity retrieval for natural language processing tasks, offering an incremental improvement over existing dual-encoder methods by better handling contextual variations in entity mentions.
The paper tackles the problem of entity retrieval by proposing MuVER, a method that constructs multi-view representations for entity descriptions and uses heuristic search to approximate optimal views for mentions, achieving state-of-the-art performance on ZESHEL and improving candidate quality on three standard Entity Linking datasets.
Entity retrieval, which aims at disambiguating mentions to canonical entities from massive KBs, is essential for many tasks in natural language processing. Recent progress in entity retrieval shows that the dual-encoder structure is a powerful and efficient framework to nominate candidates if entities are only identified by descriptions. However, they ignore the property that meanings of entity mentions diverge in different contexts and are related to various portions of descriptions, which are treated equally in previous works. In this work, we propose Multi-View Entity Representations (MuVER), a novel approach for entity retrieval that constructs multi-view representations for entity descriptions and approximates the optimal view for mentions via a heuristic searching method. Our method achieves the state-of-the-art performance on ZESHEL and improves the quality of candidates on three standard Entity Linking datasets