@inproceedings{morton-warstadt-2026-closing,
title = "Closing the Gap: Robust Multilingual Coreference Resolution with {DA}gger",
author = "Morton, Thomas and
Warstadt, Alex",
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-1.28/",
pages = "217--221",
ISBN = "979-8-89176-400-2",
abstract = "We present DAggerCoref, our submission to the CRAC 2026 Shared Task on Multilingual Coreference Resolution. DAggerCoref is a three-stage cascade built on XLM-RoBERTa-large: a gap classifier for zero pronoun detection, a mention head classifier, and a coarse-to-fine antecedent scorer. Our central contribution is applying DAgger (Ross et al., 2011) to coreference resolution: after training the antecedent scorer on gold mentions, we fine-tune on a 50/50 mix of gold and pipeline-predicted mentions, closing the train/test distribution mismatch and improving development set macro CoNLL F1 by 1.10 points. We also introduce Otsu adaptive thresholding for zero pronoun detection, which matches gold-tuned per-dataset thresholds without requiring any gold supervision. Our system achieves a macro CoNLL F1 of 67.56 on the official test set across 27 datasets and 19 languages"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="morton-warstadt-2026-closing">
<titleInfo>
<title>Closing the Gap: Robust Multilingual Coreference Resolution with DAgger</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Morton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Warstadt</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>We present DAggerCoref, our submission to the CRAC 2026 Shared Task on Multilingual Coreference Resolution. DAggerCoref is a three-stage cascade built on XLM-RoBERTa-large: a gap classifier for zero pronoun detection, a mention head classifier, and a coarse-to-fine antecedent scorer. Our central contribution is applying DAgger (Ross et al., 2011) to coreference resolution: after training the antecedent scorer on gold mentions, we fine-tune on a 50/50 mix of gold and pipeline-predicted mentions, closing the train/test distribution mismatch and improving development set macro CoNLL F1 by 1.10 points. We also introduce Otsu adaptive thresholding for zero pronoun detection, which matches gold-tuned per-dataset thresholds without requiring any gold supervision. Our system achieves a macro CoNLL F1 of 67.56 on the official test set across 27 datasets and 19 languages</abstract>
<identifier type="citekey">morton-warstadt-2026-closing</identifier>
<location>
<url>https://aclanthology.org/2026.codi-1.28/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>217</start>
<end>221</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Closing the Gap: Robust Multilingual Coreference Resolution with DAgger
%A Morton, Thomas
%A Warstadt, Alex
%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 morton-warstadt-2026-closing
%X We present DAggerCoref, our submission to the CRAC 2026 Shared Task on Multilingual Coreference Resolution. DAggerCoref is a three-stage cascade built on XLM-RoBERTa-large: a gap classifier for zero pronoun detection, a mention head classifier, and a coarse-to-fine antecedent scorer. Our central contribution is applying DAgger (Ross et al., 2011) to coreference resolution: after training the antecedent scorer on gold mentions, we fine-tune on a 50/50 mix of gold and pipeline-predicted mentions, closing the train/test distribution mismatch and improving development set macro CoNLL F1 by 1.10 points. We also introduce Otsu adaptive thresholding for zero pronoun detection, which matches gold-tuned per-dataset thresholds without requiring any gold supervision. Our system achieves a macro CoNLL F1 of 67.56 on the official test set across 27 datasets and 19 languages
%U https://aclanthology.org/2026.codi-1.28/
%P 217-221
Markdown (Informal)
[Closing the Gap: Robust Multilingual Coreference Resolution with DAgger](https://aclanthology.org/2026.codi-1.28/) (Morton & Warstadt, CODI-CRAC 2026)
ACL
- Thomas Morton and Alex Warstadt. 2026. Closing the Gap: Robust Multilingual Coreference Resolution with DAgger. 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 217–221, San Diego, California, USA. Association for Computational Linguistics.