CorPipe at CRAC 2026: Empty Nodes and Cross-Lingual Transfer in Multilingual Coreference Resolution

• URL: http://arxiv.org/abs/2605.30133v1
• Date: Thu, 28 May 2026 16:01:03 GMT
• Title: CorPipe at CRAC 2026: Empty Nodes and Cross-Lingual Transfer in Multilingual Coreference Resolution
• Abstract summary: CorPipe 26 is an improved version of CorPipe 25, with a new variant predicting empty nodes together with mentions and coreference links in a single model.<n>Our system outperforms all other submissions in the LLM track by 2.8 percent points and all submissions in the unconstrained track by 9.5 percent points.
• Score: 0.6671865055671308
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 specialized systems; additionally, 5 more datasets and 2 new languages are introduced. CorPipe 26 is an improved version of CorPipe 25, with a new variant predicting empty nodes together with mentions and coreference links in a single model. Our system outperforms all other submissions in the LLM track by 2.8 percent points and all submissions in the unconstrained track by 9.5 percent points. Furthermore, we perform a series of ablation experiments with different model sizes, empty node prediction methods, and cross-lingual zero-shot evaluation. The source code and the trained models are publicly available at https://github.com/ufal/crac2026-corpipe.

Related papers

• OSGNet with MLLM Reranking @ Ego4D Episodic Memory Challenge 2026 [75.6762616797288]
  We present our champion solutions for the Natural Language Queries and GoalStep tracks of the Ego4D Episodic Memory Challenge at CVPR 2026.<n>We propose a reranking-based framework that effectively leverages the strong video-language reasoning capability of multimodal large language model (MLLM)<n>Our method achieved first place in both the Natural Language Queries and GoalStep tracks.
  arXiv  Detail & Related papers  (2026-05-20T07:14:11Z)
• Closing the Gap at CRAC 2026: Two-Stage Adaptation for LLM-Based Multilingual Coreference Resolution [2.708757385089282]
  We present our submission to the 2026 Computational Models of Reference, Anaphora and Coreference task.<n>With an average CoNLL F1 score of 74.32 on the official test set, our system ranked first in the LLM track, and third overall.
  arXiv  Detail & Related papers  (2026-05-16T13:07:07Z)
• CorPipe at CRAC 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolution [0.6671865055671308]
  CorPipe 25 is the winning entry in the CRAC 2025 Shared Task on Multilingual Coreference Resolution.<n>Our system significantly outperforms all other submissions in both the LLM and unconstrained tracks by a substantial margin of 8 percentage points.
  arXiv  Detail & Related papers  (2025-09-22T14:51:37Z)
• CorPipe at CRAC 2024: Predicting Zero Mentions from Raw Text [1.2772632966631616]
  We present CorPipe 24, the winning entry to the CRAC 2024 Shared Task on Multilingual Coreference Resolution. In this third iteration of the task, a novel objective is to also predict empty nodes needed for zero coreference mentions. In both settings, CorPipe surpasses other participants by a large margin of 3.9 and 2.8 percent points, respectively.
  arXiv  Detail & Related papers  (2024-10-03T17:58:55Z)
• Embracing Language Inclusivity and Diversity in CLIP through Continual Language Learning [58.92843729869586]
  Vision-language pre-trained models (VL-PTMs) have advanced multimodal research in recent years, but their mastery in a few languages like English restricts their applicability in broader communities. We propose to extend VL-PTMs' language capacity by continual language learning (CLL), where a model needs to update its linguistic knowledge incrementally without suffering from catastrophic forgetting (CF) We construct a CLL benchmark covering 36 languages based on MSCOCO and XM3600 datasets and then evaluate multilingual image-text retrieval performance.
  arXiv  Detail & Related papers  (2024-01-30T17:14:05Z)
• ÚFAL CorPipe at CRAC 2023: Larger Context Improves Multilingual Coreference Resolution [1.2772632966631616]
  We present CorPipe, the winning entry in 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 participants by a large margin of 4.5 percent points.
  arXiv  Detail & Related papers  (2023-11-24T10:15:34Z)
• Ensemble Transfer Learning for Multilingual Coreference Resolution [60.409789753164944]
  A problem that frequently occurs when working with a non-English language is the scarcity of annotated training data. We design a simple but effective ensemble-based framework that combines various transfer learning techniques. We also propose a low-cost TL method that bootstraps coreference resolution models by utilizing Wikipedia anchor texts.
  arXiv  Detail & Related papers  (2023-01-22T18:22:55Z)
• 1st Place Solution of The Robust Vision Challenge (RVC) 2022 Semantic Segmentation Track [67.56316745239629]
  This report describes the winning solution to the semantic segmentation task of the Robust Vision Challenge on ECCV 2022. Our method adopts the FAN-B-Hybrid model as the encoder and uses Segformer as the segmentation framework. The proposed method could serve as a strong baseline for the multi-domain segmentation task and benefit future works.
  arXiv  Detail & Related papers  (2022-10-23T20:52:22Z)
• ÚFAL CorPipe at CRAC 2022: Effectivity of Multilingual Models for Coreference Resolution [1.7871207544302354]
  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-maximization approach.
  arXiv  Detail & Related papers  (2022-09-15T13:11:39Z)
• Unifying Language Learning Paradigms [96.35981503087567]
  We present a unified framework for pre-training models that are universally effective across datasets and setups. We show how different pre-training objectives can be cast as one another and how interpolating between different objectives can be effective. Our model also achieve strong results at in-context learning, outperforming 175B GPT-3 on zero-shot SuperGLUE and tripling the performance of T5-XXL on one-shot summarization.
  arXiv  Detail & Related papers  (2022-05-10T19:32:20Z)
• Explicit Alignment Objectives for Multilingual Bidirectional Encoders [111.65322283420805]
  We present a new method for learning multilingual encoders, AMBER (Aligned Multilingual Bi-directional EncodeR) AMBER is trained on additional parallel data using two explicit alignment objectives that align the multilingual representations at different granularities. Experimental results show that AMBER obtains gains of up to 1.1 average F1 score on sequence tagging and up to 27.3 average accuracy on retrieval over the XLMR-large model.
  arXiv  Detail & Related papers  (2020-10-15T18:34:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.