Overview of the NLPCC 2024 Shared Task 3: Dialogue-Level Coreference Resolution and Relation Extraction

Yiyun Xiong, Fei Li, Bobo Li, Hao Fei, Donghong Ji, Chong Teng

Abstract: In this report, we give an overview of the shared task about dialogue-level coreference resolution and relation extraction at the 13th CCF Conference on Natural Language Processing and Chinese Computing (NLPCC 2024). Dialogue Relation Extraction (DRE) focuses on the relations between arguments in a conversation, which can help better understand the interaction between interlocutors. The phenomenon of coreference is widely present in natural language, especially in conversations. Dialogue Coreference Resolution (DCR) can provide more accurate contextual understanding for the DRE task. We introduce dialogue-level joint coreference resolution and relation extraction task, and evaluate the ability of models to recognize dialogue-level coreference information and extract relations using coreference information. We describe the participating systems and their results to show the up-to-date progress in the DRE and DCR tasks, providing guidelines for future research.