Focusing on Context is NICE: Improving Overshadowed Entity Disambiguation
This work addresses a specific challenge in entity disambiguation for natural language processing applications, representing an incremental improvement over existing methods.
The paper tackled the problem of entity overshadowing in entity disambiguation, where models incorrectly prioritize frequent entities over contextually relevant ones, and introduced NICE, an iterative method using entity type information to improve performance on overshadowed entities while remaining competitive on frequent ones.
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.