Major Entity Identification: A Generalizable Alternative to Coreference Resolution
This addresses the generalization bottleneck in coreference resolution for NLP applications, offering a practical alternative that reduces reliance on additional annotated data.
The paper tackles the limited generalization of coreference resolution models by proposing Major Entity Identification (MEI), an alternative task that assumes target entities are specified and focuses on frequent entities, demonstrating strong cross-domain generalization on multiple datasets with supervised models and LLM-based few-shot prompting.
The limited generalization of coreference resolution (CR) models has been a major bottleneck in the task's broad application. Prior work has identified annotation differences, especially for mention detection, as one of the main reasons for the generalization gap and proposed using additional annotated target domain data. Rather than relying on this additional annotation, we propose an alternative referential task, Major Entity Identification (MEI), where we: (a) assume the target entities to be specified in the input, and (b) limit the task to only the frequent entities. Through extensive experiments, we demonstrate that MEI models generalize well across domains on multiple datasets with supervised models and LLM-based few-shot prompting. Additionally, MEI fits the classification framework, which enables the use of robust and intuitive classification-based metrics. Finally, MEI is also of practical use as it allows a user to search for all mentions of a particular entity or a group of entities of interest.