Entity Tagging: Extracting Entities in Text Without Mention Supervision

TL;DR

This paper shows that for entity extraction tasks focusing solely on the set of entities, mention boundary detection can be skipped, as a mention-agnostic model performs comparably to traditional mention-aware methods.

Contribution

The paper introduces the Entity Tagging formulation and demonstrates that mention detection is unnecessary for certain entity extraction tasks, enabling simpler models like GET to perform well.

Findings

GET achieves comparable performance to mention-aware models.

Mention detection does not significantly improve entity extraction in set-focused tasks.

Models trained on partial annotations perform well across benchmarks.

Abstract

Detection and disambiguation of all entities in text is a crucial task for a wide range of applications. The typical formulation of the problem involves two stages: detect mention boundaries and link all mentions to a knowledge base. For a long time, mention detection has been considered as a necessary step for extracting all entities in a piece of text, even if the information about mention spans is ignored by some downstream applications that merely focus on the set of extracted entities. In this paper we show that, in such cases, detection of mention boundaries does not bring any considerable performance gain in extracting entities, and therefore can be skipped. To conduct our analysis, we propose an "Entity Tagging" formulation of the problem, where models are evaluated purely on the set of extracted entities without considering mentions. We compare a state-of-the-art mention-aware entity linking solution against GET, a mention-agnostic sequence-to-sequence model that simply outputs a list of disambiguated entities given an input context. We find that these models achieve comparable performance when trained both on a fully and partially annotated dataset across multiple benchmarks, demonstrating that GET can extract disambiguated entities with strong performance without explicit mention boundaries supervision.