多语言共指消解新模型，性能远超其他参赛系统
CorPipe at CRAC 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolution
- 基于PyTorch重写系统，适配大模型与传统双轨评测
- 在两个赛道均领先第二名8个百分点，表现显著提升
- 适合多语言自然语言处理研究者参考复现
本文介绍CorPipe 25，即2025年CRAC多语言共指消解共享任务的优胜方案。该任务第四次举办，新增大模型（LLM）赛道，同时缩减开发集与测试集以降低计算成本，并引入额外数据集。CorPipe 25是对以往系统的全面重构，从TensorFlow迁移至PyTorch。在大模型与非受限双赛道中，本系统均以8个百分点的显著优势超越所有其他提交结果。源代码与训练模型已公开于https://github.com/ufal/crac2025-corpipe。
原文摘要 · Abstract (English)
We present CorPipe 25, the winning entry to the CRAC 2025 Shared Task on Multilingual Coreference Resolution. This fourth iteration of the shared task introduces a new LLM track alongside the original unconstrained track, features reduced development and test sets to lower computational requirements, and includes additional datasets. CorPipe 25 represents a complete reimplementation of our previous systems, migrating from TensorFlow to PyTorch. Our system significantly outperforms all other submissions in both the LLM and unconstrained tracks by a substantial margin of 8 percentage points. The source code and trained models are publicly available at https://github.com/ufal/crac2025-corpipe.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。