<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="steigerwald-etal-2026-nurnberg">
    <titleInfo>
        <title>Nürnberg NLP at PsyDefDetect: Multi-Axis Voter Ensembles for Psychological Defence Mechanism Classification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Philipp</namePart>
        <namePart type="family">Steigerwald</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Eric</namePart>
        <namePart type="family">Rudolph</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jens</namePart>
        <namePart type="family">Albrecht</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 BioNLP 2026 (Shared Tasks)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Deepak</namePart>
            <namePart type="family">Gupta</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Dina</namePart>
            <namePart type="family">Demner-Fushman</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">979-8-89176-435-4</identifier>
    </relatedItem>
    <abstract>Detecting levels of psychological defence mechanisms in supportive conversations is inherently ambiguous. In the PsyDefDetect shared task at BioNLP 2026 the eight positive defence categories share surface language and differ only in pragmatic function and trained raters reach only moderate inter-annotator agreement. On such a task the decisive lever is not a stronger single model but error independence, since any single representation will waver on the overlapping defence boundaries. We translate this insight into a 9-voter ensemble spanning three orthogonal axes: class granularity (all nine classes for the gatekeeper, only the eight defence classes for the specialists), training method (generative and discriminative) and base model. The system reaches an F1 score of .420 on the hidden test set, placing first among 21 registered teams.</abstract>
    <identifier type="citekey">steigerwald-etal-2026-nurnberg</identifier>
    <location>
        <url>https://aclanthology.org/2026.bionlp-2.9/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>59</start>
            <end>65</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Nürnberg NLP at PsyDefDetect: Multi-Axis Voter Ensembles for Psychological Defence Mechanism Classification
%A Steigerwald, Philipp
%A Rudolph, Eric
%A Albrecht, Jens
%Y Gupta, Deepak
%Y Demner-Fushman, Dina
%S Proceedings of the BioNLP 2026 (Shared Tasks)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-435-4
%F steigerwald-etal-2026-nurnberg
%X Detecting levels of psychological defence mechanisms in supportive conversations is inherently ambiguous. In the PsyDefDetect shared task at BioNLP 2026 the eight positive defence categories share surface language and differ only in pragmatic function and trained raters reach only moderate inter-annotator agreement. On such a task the decisive lever is not a stronger single model but error independence, since any single representation will waver on the overlapping defence boundaries. We translate this insight into a 9-voter ensemble spanning three orthogonal axes: class granularity (all nine classes for the gatekeeper, only the eight defence classes for the specialists), training method (generative and discriminative) and base model. The system reaches an F1 score of .420 on the hidden test set, placing first among 21 registered teams.
%U https://aclanthology.org/2026.bionlp-2.9/
%P 59-65

Markdown (Informal)

[Nürnberg NLP at PsyDefDetect: Multi-Axis Voter Ensembles for Psychological Defence Mechanism Classification](https://aclanthology.org/2026.bionlp-2.9/) (Steigerwald et al., BioNLP 2026)

• Nürnberg NLP at PsyDefDetect: Multi-Axis Voter Ensembles for Psychological Defence Mechanism Classification (Steigerwald et al., BioNLP 2026)

ACL

• Philipp Steigerwald, Eric Rudolph, and Jens Albrecht. 2026. Nürnberg NLP at PsyDefDetect: Multi-Axis Voter Ensembles for Psychological Defence Mechanism Classification. In Proceedings of the BioNLP 2026 (Shared Tasks), pages 59–65, San Diego, California, USA. Association for Computational Linguistics.