Major Entity Identification: A Generalizable Alternative to Coreference Resolution

TL;DR

This paper introduces Major Entity Identification (MEI), a new task that improves cross-domain generalization in entity recognition by focusing on frequent entities and assuming target entities are specified, avoiding reliance on additional annotations.

Contribution

The paper proposes MEI as a generalizable alternative to coreference resolution, demonstrating its effectiveness across domains and its practical utility for entity search.

Findings

MEI models generalize well across multiple datasets and domains.

MEI enables the use of classification metrics for evaluation.

MEI allows efficient search for mentions of specific entities.

Abstract

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.