GUMBridge: a Corpus for Varieties of Bridging Anaphora

TL;DR

GUMBridge is a comprehensive, genre-diverse corpus for bridging anaphora in English, enabling better understanding and analysis of this complex linguistic phenomenon across various contexts.

Contribution

The paper introduces GUMBridge, a large, multi-genre corpus with detailed annotations for bridging anaphora, filling gaps in existing resources and supporting advanced NLP research.

Findings

Annotation quality is high and reliable.

Baseline models struggle with bridging resolution.

Subtype classification remains challenging for LLMs.

Abstract

Bridging is an anaphoric phenomenon where the referent of an entity in a discourse is dependent on a previous, non-identical entity for interpretation, such as in "There is 'a house'. 'The door' is red," where the door is specifically understood to be the door of the aforementioned house. While there are several existing resources in English for bridging anaphora, most are small, provide limited coverage of the phenomenon, and/or provide limited genre coverage. In this paper, we introduce GUMBridge, a new resource for bridging, which includes 16 diverse genres of English, providing both broad coverage for the phenomenon and granular annotations for the subtype categorization of bridging varieties. We also present an evaluation of annotation quality and report on baseline performance using open and closed source contemporary LLMs on three tasks underlying our data, showing that bridging resolution and subtype classification remain difficult NLP tasks in the age of LLMs.