DialogRE^C+: An Extension of DialogRE to Investigate How Much Coreference Helps Relation Extraction in Dialogs

TL;DR

This paper introduces DialogRE^C+, a new dataset and models that incorporate coreference resolution to improve dialogue relation extraction, demonstrating that explicit coreference knowledge enhances relation reasoning in dialogues.

Contribution

The work presents a new annotated dataset with coreference chains and develops coreference-enhanced models for dialogue relation extraction, advancing the integration of coreference information in DRE.

Findings

Coreference knowledge improves DRE performance.

New dataset with 5,068 coreference chains annotated.

Coreference-enhanced models outperform baseline methods.

Abstract

Dialogue relation extraction (DRE) that identifies the relations between argument pairs in dialogue text, suffers much from the frequent occurrence of personal pronouns, or entity and speaker coreference. This work introduces a new benchmark dataset DialogRE^C+, introducing coreference resolution into the DRE scenario. With the aid of high-quality coreference knowledge, the reasoning of argument relations is expected to be enhanced. In DialogRE^C+ dataset, we manually annotate total 5,068 coreference chains over 36,369 argument mentions based on the existing DialogRE data, where four different coreference chain types namely speaker chain, person chain, location chain and organization chain are explicitly marked. We further develop 4 coreference-enhanced graph-based DRE models, which learn effective coreference representations for improving the DRE task. We also train a coreference resolution model based on our annotations and evaluate the effect of automatically extracted coreference chains demonstrating the practicality of our dataset and its potential to other domains and tasks.