xcore-litbank

xCoRe LitBank

Official weights for xcore trained on litbank and based on DeBERTa-large. This model achieves 78.2 Avg CoNLL-F1 on LitBank.

Other available models at SapienzaNLP huggingface hub:

<!-- | ["sapienzanlp/xcore-litbank"](https://huggingface.co/sapienzanlp/xcore-all) | LitBank, ECB+, BookCoref_silver, SciCo, OntoNotes, PreCo | - | All datasets |--> <!-- | ["sapienzanlp/xcore-bookcoref"](https://huggingface.co/sapienzanlp/xcore-bookcoref) | [BookCoref](https://huggingface.co/datasets/sapienzanlp/bookcoref) | 62.3 | Single Document (Full Books) |-->

Results on OntoNotes

<img src="https://cdn-uploads.huggingface.co/production/uploads/65e9ccd84ce78d665a50f78b/ChwqWP3Fs-cNo1So3I_fI.png" alt="drawing" width="95%"/>

xCoRe: Cross Context Coreference Resolution Defying recent trends

Citation

This work has been published at EMNLP 2025 main conference. If you use any part, please consider citing our paper as follows:

@inproceedings{martinelli-etal-2025-xcore,
    title = "x{C}o{R}e: Cross-context Coreference Resolution",
    author = "Martinelli, Giuliano  and
      Gatti, Bruno  and
      Navigli, Roberto",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.emnlp-main.1737/",
    pages = "34252--34266"
}