<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fu-etal-2026-translation">
    <titleInfo>
        <title>Does Translation Preserve Character Personality? Quantifying Perceived Character-Personality Consistency Across Languages</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xinger</namePart>
        <namePart type="family">Fu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Masaaki</namePart>
        <namePart type="family">Nagata</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chenhui</namePart>
        <namePart type="family">Chu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ruifeng</namePart>
            <namePart type="family">Xu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ayu</namePart>
            <namePart type="family">Purwarianti</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tong</namePart>
            <namePart type="family">Rong</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jun</namePart>
            <namePart type="family">Suzuki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hengqin, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-439-2</identifier>
    </relatedItem>
    <abstract>Translation conveys meaning across languages, but does it preserve the personality a character conveys? We introduce an evaluation framework for quantifying how well translation systems maintain perceived character personality, the personality impression a reader forms from a character’s dialogue, described along the five Big Five dimensions; we use these dimensions as descriptive labels for the impression, not as a psychometric measurement of the character. Our framework applies personality predictors to both source and translated utterances, measuring cross-lingual consistency via Spearman rank correlation at the speaker level. We study entertainment subtitle translation, where every utterance is produced by a named character, and compare evaluation conditions that include, shuffle, or withhold the character names. We evaluate five MT systems, including dedicated MT APIs (Google Translate, DeepL) and LLMs (GPT-4o, Qwen3- 32B, Aya-expanse-32B), and additionally report human translation as a reference condition on GAME OF THRONES (English→12 target languages, 11 characters) and ONE PIECE (Japanese→English, 15 characters). Under our evaluation protocol, measured personality consistency varies across systems and language pairs, and high BLEU/COMET translation quality does not reliably imply high personality consistency.</abstract>
    <identifier type="citekey">fu-etal-2026-translation</identifier>
    <location>
        <url>https://aclanthology.org/2026.aacl-long.195/</url>
    </location>
    <part>
        <date>2026-11</date>
        <extent unit="page">
            <start>4338</start>
            <end>4358</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Does Translation Preserve Character Personality? Quantifying Perceived Character-Personality Consistency Across Languages
%A Fu, Xinger
%A Nagata, Masaaki
%A Chu, Chenhui
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F fu-etal-2026-translation
%X Translation conveys meaning across languages, but does it preserve the personality a character conveys? We introduce an evaluation framework for quantifying how well translation systems maintain perceived character personality, the personality impression a reader forms from a character’s dialogue, described along the five Big Five dimensions; we use these dimensions as descriptive labels for the impression, not as a psychometric measurement of the character. Our framework applies personality predictors to both source and translated utterances, measuring cross-lingual consistency via Spearman rank correlation at the speaker level. We study entertainment subtitle translation, where every utterance is produced by a named character, and compare evaluation conditions that include, shuffle, or withhold the character names. We evaluate five MT systems, including dedicated MT APIs (Google Translate, DeepL) and LLMs (GPT-4o, Qwen3- 32B, Aya-expanse-32B), and additionally report human translation as a reference condition on GAME OF THRONES (English→12 target languages, 11 characters) and ONE PIECE (Japanese→English, 15 characters). Under our evaluation protocol, measured personality consistency varies across systems and language pairs, and high BLEU/COMET translation quality does not reliably imply high personality consistency.
%U https://aclanthology.org/2026.aacl-long.195/
%P 4338-4358

Markdown (Informal)

[Does Translation Preserve Character Personality? Quantifying Perceived Character-Personality Consistency Across Languages](https://aclanthology.org/2026.aacl-long.195/) (Fu et al., AACL-IJCNLP 2026)

• Does Translation Preserve Character Personality? Quantifying Perceived Character-Personality Consistency Across Languages (Fu et al., AACL-IJCNLP 2026)

ACL

• Xinger Fu, Masaaki Nagata, and Chenhui Chu. 2026. Does Translation Preserve Character Personality? Quantifying Perceived Character-Personality Consistency Across Languages. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4338–4358, Hengqin, China. Association for Computational Linguistics.