Tag
This paper proposes a novel pipeline for multilingual coreference resolution that uses cycle-consistent machine translation from English to low-resource languages to generate training data, validated by back-translation and BERT similarity. Experiments on four low-resource languages show significant performance gains, enabling accurate coreference resolution where no prior corpora existed.
This paper presents a two-stage adaptation method for LLM-based multilingual coreference resolution, achieving first place in the LLM track of CRAC 2026 with a CoNLL F1 of 74.32. The approach fine-tunes Gemma-3-27b using a multilingual base adapter followed by dataset-specific adapters.