# 'UFAL CorPipe at CRAC 2023: Larger Context Improves Multilingual Coreference Resolution

arXiv: https://arxiv.org/abs/2311.14391 · HTML: https://mlsanity.com/paper/2311.14391/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 25 references that are in the map.
- First posted on arXiv 24 Nov 2023.

## Builds on (most cited first, 2 of 2)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models](https://mlsanity.com/paper/2301.10472/) (2023)

## Built on by (most cited first, 7 of 7)

- [CorPipe at CRAC 2024: Predicting Zero Mentions from Raw Text](https://mlsanity.com/paper/2410.02756/) (2024)
- [Exploring Multiple Strategies to Improve Multilingual Coreference Resolution in CorefUD](https://mlsanity.com/paper/2408.16893/) (2024)
- [CorPipe at CRAC 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolution](https://mlsanity.com/paper/2509.17858/) (2025)
- [Towards Generating Automatic Anaphora Annotations](https://mlsanity.com/paper/2503.09417/) (2025)
- [CorefInst: Leveraging LLMs for Multilingual Coreference Resolution](https://mlsanity.com/paper/2509.17505/) (2025)
- [CorPipe at CRAC 2026: Empty Nodes and Cross-Lingual Transfer in Multilingual Coreference Resolution](https://mlsanity.com/paper/2605.30133/) (2026)
- [Multilingual Coreference Resolution via Cycle-Consistent Machine Translation](https://mlsanity.com/paper/2606.05444/) (2026)

## Abstract (arXiv)

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 participants by a large margin of 4.5 percent points. CorPipe first performs mention detection, followed by coreference linking via an antecedent-maximization approach on the retrieved spans. Both tasks are trained jointly on all available corpora using a shared pretrained language model. Our main improvements comprise inputs larger than 512 subwords and changing the mention decoding to support ensembling. The source code is available at https://github.com/ufal/crac2023-corpipe.