CorPipe at CRAC 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolution

• URL: http://arxiv.org/abs/2509.17858v2
• Date: Thu, 06 Nov 2025 08:02:58 GMT
• Title: CorPipe at CRAC 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolution
• Abstract summary: 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.
• Score: 0.6671865055671308
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• CorPipe at CRAC 2026: Empty Nodes and Cross-Lingual Transfer in Multilingual Coreference Resolution [0.6671865055671308]
  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.
  arXiv  Detail & Related papers  (2026-05-28T16:01:03Z)
• 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)
• Themis: Training Robust Multilingual Code Reward Models for Flexible Multi-Criteria Scoring [51.497900015187675]
  We develop Themis-CodePreference, the largest open-source collection of code preferences to date, and use it to train Themis-RM, a suite of multilingual code reward models.<n>Our experiments and ablations demonstrate positive scaling trends, strong cross-lingual transfer when training on diverse preferences.
  arXiv  Detail & Related papers  (2026-05-01T16:07:34Z)
• Residual Context Diffusion Language Models [90.07635240595926]
  Residual Context Diffusion (RCD) is a module that converts discarded token representations into contextual residuals and injects them back for the next denoising step.<n>RCD consistently improves frontier dLLMs by 5-10 points in accuracy with minimal extra computation overhead.
  arXiv  Detail & Related papers  (2026-01-30T13:16:32Z)
• DeDisCo at the DISRPT 2025 Shared Task: A System for Discourse Relation Classification [6.070010259231488]
  This paper presents DeDisCo, Georgetown University's entry in the DISRPT 2025 shared task on discourse relation classification.<n>We test two approaches, using an mt5-based encoder and a decoder based approach using the openly available Qwen model.<n>Our system achieves a macro-accuracy score of 71.28, and we provide some interpretation and error analysis for our results.
  arXiv  Detail & Related papers  (2025-09-15T01:25:37Z)
• UnitCoder: Scalable Iterative Code Synthesis with Unit Test Guidance [65.01483640267885]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in various tasks, yet code generation remains a major challenge.<n>We introduce UnitCoder, a systematic pipeline leveraging model-generated unit tests to guide and validate the code generation process.<n>Our work presents a scalable approach that leverages model-generated unit tests to guide the synthesis of high-quality code data from pre-training corpora.
  arXiv  Detail & Related papers  (2025-02-17T05:37:02Z)
• 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)
• 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)
• NAVER LABS Europe's Multilingual Speech Translation Systems for the IWSLT 2023 Low-Resource Track [78.80683163990446]
  This paper presents NAVER LABS Europe's systems for Tamasheq-French and Quechua-Spanish speech translation in the IWSLT 2023 Low-Resource track. Our work attempts to maximize translation quality in low-resource settings using multilingual parameter-efficient solutions.
  arXiv  Detail & Related papers  (2023-06-13T13:22:30Z)
• CodeT5+: Open Code Large Language Models for Code Understanding and Generation [72.1638273937025]
  Large language models (LLMs) pretrained on vast source code have achieved prominent progress in code intelligence. CodeT5+ is a family of encoder-decoder LLMs for code in which component modules can be flexibly combined to suit a wide range of downstream code tasks. We extensively evaluate CodeT5+ on over 20 code-related benchmarks in different settings, including zero-shot, finetuning, and instruction-tuning.
  arXiv  Detail & Related papers  (2023-05-13T14:23:07Z)
• 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)
• Multilingual Machine Translation Systems from Microsoft for WMT21 Shared Task [95.06453182273027]
  This report describes Microsoft's machine translation systems for the WMT21 shared task on large-scale multilingual machine translation. Our model submissions to the shared task were with DeltaLMnotefooturlhttps://aka.ms/deltalm, a generic pre-trained multilingual-decoder model. Our final submissions ranked first on three tracks in terms of the automatic evaluation metric.
  arXiv  Detail & Related papers  (2021-11-03T09:16:17Z)
• Palomino-Ochoa at SemEval-2020 Task 9: Robust System based on Transformer for Code-Mixed Sentiment Classification [1.6244541005112747]
  We present a transfer learning system to perform a mixed Spanish-English sentiment classification task. Our proposal uses the state-of-the-art language model BERT and embed it within a ULMFiT transfer learning pipeline.
  arXiv  Detail & Related papers  (2020-11-18T18:25:58Z)
• Learning Delicate Local Representations for Multi-Person Pose Estimation [77.53144055780423]
  We propose a novel method called Residual Steps Network (RSN) RSN aggregates features with the same spatial size (Intra-level features) efficiently to obtain delicate local representations. Our approach won the 1st place of COCO Keypoint Challenge 2019.
  arXiv  Detail & Related papers  (2020-03-09T10:40:49Z)

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.