Generative Multilingual Coreference Resolution at CRAC 2026

Jakub Hejman; Ondřej Pražák; Miloslav Konopík

Generative Multilingual Coreference Resolution at CRAC 2026

Jakub Hejman, Ondrej Prazak, Miloslav Konopík

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use <b>...</b> for bold, <i>...</i> for italic, and <url>...</url> for URLs.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

Participating again in this year’s edition of the CRAC shared task on coreference resolution, we present our upgraded system with an official uplift of 15.46 percentage points in CoNLL-U score. We incorporated the larger Gemma 3 27B IT model, joint pre-training, headword tagging, more efficient training and inference as well as a sliding window to achieve this result. Our system placed second in the LLM track and third overall with a primary score of 73.83. We reached the highest scores on two datasets. Finally, we compare specialized and general LLM approaches.

Anthology ID:: 2026.codi-1.22
Volume:: Proceedings of the 2nd Joint Workshop on Computational Approaches to Discourse, Context and Document-Level Inferences and Computational Models of Reference, Anaphora and Coreference (CODI-CRAC 2026)
Month:: July
Year:: 2026
Address:: San Diego, California, USA
Editors:: Chloé Braud, Christian Hardmeier, Maciej Ogrodniczuk, Sharid Loaiciga, Amir Zeldes, Michal Novák, Chuyuan Li, Michael Strube, Junyi Jessy Li
Venues:: CODI | CRAC | WS
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 162–166
Language:
URL:: https://aclanthology.org/2026.codi-1.22/
DOI:
Bibkey:
Cite (ACL):: Jakub Hejman, Ondrej Prazak, and Miloslav Konopík. 2026. Generative Multilingual Coreference Resolution at CRAC 2026. In Proceedings of the 2nd Joint Workshop on Computational Approaches to Discourse, Context and Document-Level Inferences and Computational Models of Reference, Anaphora and Coreference (CODI-CRAC 2026), pages 162–166, San Diego, California, USA. Association for Computational Linguistics.
Cite (Informal):: Generative Multilingual Coreference Resolution at CRAC 2026 (Hejman et al., CODI-CRAC 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.codi-1.22.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{hejman-etal-2026-generative,
    title = "Generative Multilingual Coreference Resolution at {CRAC} 2026",
    author = "Hejman, Jakub  and
      Prazak, Ondrej  and
      Konop{\'i}k, Miloslav",
    editor = "Braud, Chlo{\'e}  and
      Hardmeier, Christian  and
      Ogrodniczuk, Maciej  and
      Loaiciga, Sharid  and
      Zeldes, Amir  and
      Nov{\'a}k, Michal  and
      Li, Chuyuan  and
      Strube, Michael  and
      Li, Junyi Jessy",
    booktitle = "Proceedings of the 2nd Joint Workshop on Computational Approaches to Discourse, Context and Document-Level Inferences and Computational Models of Reference, Anaphora and Coreference ({CODI}-{CRAC} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.codi-1.22/",
    pages = "162--166",
    ISBN = "979-8-89176-400-2",
    abstract = "Participating again in this year{'}s edition of the CRAC shared task on coreference resolution, we present our upgraded system with an official uplift of 15.46 percentage points in CoNLL-U score. We incorporated the larger Gemma 3 27B IT model, joint pre-training, headword tagging, more efficient training and inference as well as a sliding window to achieve this result. Our system placed second in the LLM track and third overall with a primary score of 73.83. We reached the highest scores on two datasets. Finally, we compare specialized and general LLM approaches."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hejman-etal-2026-generative">
    <titleInfo>
        <title>Generative Multilingual Coreference Resolution at CRAC 2026</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jakub</namePart>
        <namePart type="family">Hejman</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ondrej</namePart>
        <namePart type="family">Prazak</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Miloslav</namePart>
        <namePart type="family">Konopík</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2nd Joint Workshop on Computational Approaches to Discourse, Context and Document-Level Inferences and Computational Models of Reference, Anaphora and Coreference (CODI-CRAC 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Chloé</namePart>
            <namePart type="family">Braud</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Christian</namePart>
            <namePart type="family">Hardmeier</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Maciej</namePart>
            <namePart type="family">Ogrodniczuk</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sharid</namePart>
            <namePart type="family">Loaiciga</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Amir</namePart>
            <namePart type="family">Zeldes</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Michal</namePart>
            <namePart type="family">Novák</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Chuyuan</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Michael</namePart>
            <namePart type="family">Strube</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Junyi</namePart>
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-400-2</identifier>
    </relatedItem>
    <abstract>Participating again in this year’s edition of the CRAC shared task on coreference resolution, we present our upgraded system with an official uplift of 15.46 percentage points in CoNLL-U score. We incorporated the larger Gemma 3 27B IT model, joint pre-training, headword tagging, more efficient training and inference as well as a sliding window to achieve this result. Our system placed second in the LLM track and third overall with a primary score of 73.83. We reached the highest scores on two datasets. Finally, we compare specialized and general LLM approaches.</abstract>
    <identifier type="citekey">hejman-etal-2026-generative</identifier>
    <location>
        <url>https://aclanthology.org/2026.codi-1.22/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>162</start>
            <end>166</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Generative Multilingual Coreference Resolution at CRAC 2026
%A Hejman, Jakub
%A Prazak, Ondrej
%A Konopík, Miloslav
%Y Braud, Chloé
%Y Hardmeier, Christian
%Y Ogrodniczuk, Maciej
%Y Loaiciga, Sharid
%Y Zeldes, Amir
%Y Novák, Michal
%Y Li, Chuyuan
%Y Strube, Michael
%Y Li, Junyi Jessy
%S Proceedings of the 2nd Joint Workshop on Computational Approaches to Discourse, Context and Document-Level Inferences and Computational Models of Reference, Anaphora and Coreference (CODI-CRAC 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-400-2
%F hejman-etal-2026-generative
%X Participating again in this year’s edition of the CRAC shared task on coreference resolution, we present our upgraded system with an official uplift of 15.46 percentage points in CoNLL-U score. We incorporated the larger Gemma 3 27B IT model, joint pre-training, headword tagging, more efficient training and inference as well as a sliding window to achieve this result. Our system placed second in the LLM track and third overall with a primary score of 73.83. We reached the highest scores on two datasets. Finally, we compare specialized and general LLM approaches.
%U https://aclanthology.org/2026.codi-1.22/
%P 162-166

Download as File

Markdown (Informal)

[Generative Multilingual Coreference Resolution at CRAC 2026](https://aclanthology.org/2026.codi-1.22/) (Hejman et al., CODI-CRAC 2026)

Generative Multilingual Coreference Resolution at CRAC 2026 (Hejman et al., CODI-CRAC 2026)

ACL

Jakub Hejman, Ondrej Prazak, and Miloslav Konopík. 2026. Generative Multilingual Coreference Resolution at CRAC 2026. In Proceedings of the 2nd Joint Workshop on Computational Approaches to Discourse, Context and Document-Level Inferences and Computational Models of Reference, Anaphora and Coreference (CODI-CRAC 2026), pages 162–166, San Diego, California, USA. Association for Computational Linguistics.