CorPipe at CRAC 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolution
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Coreference ResolutionSimilar Papers 제목 키워드 기반
ÚFAL CorPipe at CRAC 2023: Larger Context Improves Multilingual Coreference Resolution
We present CorPipe, the winning entry to the CRAC 2023 Shared Task on Multilingual Coreference Resolution. Our system is an improved version of our earlier multilingual coreference pipeline, and it surpasses other partic…
coreference-resolutionCoreference ResolutionLanguage ModelingLanguage ModellingCorPipe at CRAC 2026: Empty Nodes and Cross-Lingual Transfer in Multilingual Coreference Resolution
We introduce CorPipe 26, our winning submission to the CRAC 2026 Shared Task on Multilingual Coreference Resolution. The fifth edition of this shared task focuses mainly on the comparison of generative LLMs and specializ…
Cross-Lingual TransferCoreference ResolutionÚFAL CorPipe at CRAC 2022: Effectivity of Multilingual Models for Coreference Resolution
We describe the winning submission to the CRAC 2022 Shared Task on Multilingual Coreference Resolution. Our system first solves mention detection and then coreference linking on the retrieved spans with an antecedent-max…
coreference-resolutionCoreference ResolutionCorPipe at CRAC 2024: Predicting Zero Mentions from Raw Text
We present CorPipe 24, the winning entry to the CRAC 2024 Shared Task on Multilingual Coreference Resolution. In this third iteration of the shared task, a novel objective is to also predict empty nodes needed for zero c…
coreference-resolutionCoreference ResolutionSentenceCorefInst: Leveraging LLMs for Multilingual Coreference Resolution
Coreference Resolution (CR) is a crucial yet challenging task in natural language understanding, often constrained by task-specific architectures and encoder-based language models that demand extensive training and lack …
Natural Language UnderstandingCoreference Resolution