@inproceedings{takahashi-etal-2026-challenges,
title = "Challenges in {J}apanese Euphemism Classification: An Analysis of Pretrained {J}apanese and Multilingual Models",
author = "Takahashi, Noriko and
Poh, Whitney and
Barak, Libby and
Peng, JIng and
Feldman, Anna",
editor = "Egg, Markus and
Kordoni, Valia",
booktitle = "Proceedings of Learning Non-Literal Expressions with Small Data @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.nonliteral-1.1/",
doi = "10.63317/234ssv2bkqd2",
pages = "1--11",
abstract = "Euphemisms present a persistent challenge for NLP because their interpretation depends on pragmatic inference, social norms, and contextual cues rather than surface meaning alone. Although Potentially Euphemistic Terms (PET)-based resources have been developed for several languages, Japanese euphemisms remain computationally unexplored despite their close interaction with honorifics, register variation, and orthographic choice. We introduce JP-PET, the first PET-based dataset for Japanese euphemism classification, comprising 1,672 annotated sentences across 101 PETs and ten semantic domains with register metadata. We evaluate two Japanese monolingual transformer models (Rinna RoBERTa and Tohoku BERT) and the multilingual XLM-R under three controlled PET-level data splits that isolate lexical familiarity and generalization to unseen euphemisms. While models achieve strong performance when PETs are shared between training and test data, performance drops substantially under PET-disjoint conditions, indicating reliance on lexical familiarity. Error analysis reveals systematic challenges in politically conventionalized expressions, metaphor-based euphemisms, and orthographic mitigation strategies. JP-PET provides the first benchmark for studying pragmatic meaning in Japanese NLP."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="takahashi-etal-2026-challenges">
<titleInfo>
<title>Challenges in Japanese Euphemism Classification: An Analysis of Pretrained Japanese and Multilingual Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Noriko</namePart>
<namePart type="family">Takahashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Whitney</namePart>
<namePart type="family">Poh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Libby</namePart>
<namePart type="family">Barak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">JIng</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Feldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Learning Non-Literal Expressions with Small Data @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Markus</namePart>
<namePart type="family">Egg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valia</namePart>
<namePart type="family">Kordoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Euphemisms present a persistent challenge for NLP because their interpretation depends on pragmatic inference, social norms, and contextual cues rather than surface meaning alone. Although Potentially Euphemistic Terms (PET)-based resources have been developed for several languages, Japanese euphemisms remain computationally unexplored despite their close interaction with honorifics, register variation, and orthographic choice. We introduce JP-PET, the first PET-based dataset for Japanese euphemism classification, comprising 1,672 annotated sentences across 101 PETs and ten semantic domains with register metadata. We evaluate two Japanese monolingual transformer models (Rinna RoBERTa and Tohoku BERT) and the multilingual XLM-R under three controlled PET-level data splits that isolate lexical familiarity and generalization to unseen euphemisms. While models achieve strong performance when PETs are shared between training and test data, performance drops substantially under PET-disjoint conditions, indicating reliance on lexical familiarity. Error analysis reveals systematic challenges in politically conventionalized expressions, metaphor-based euphemisms, and orthographic mitigation strategies. JP-PET provides the first benchmark for studying pragmatic meaning in Japanese NLP.</abstract>
<identifier type="citekey">takahashi-etal-2026-challenges</identifier>
<identifier type="doi">10.63317/234ssv2bkqd2</identifier>
<location>
<url>https://aclanthology.org/2026.nonliteral-1.1/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1</start>
<end>11</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Challenges in Japanese Euphemism Classification: An Analysis of Pretrained Japanese and Multilingual Models
%A Takahashi, Noriko
%A Poh, Whitney
%A Barak, Libby
%A Peng, JIng
%A Feldman, Anna
%Y Egg, Markus
%Y Kordoni, Valia
%S Proceedings of Learning Non-Literal Expressions with Small Data @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F takahashi-etal-2026-challenges
%X Euphemisms present a persistent challenge for NLP because their interpretation depends on pragmatic inference, social norms, and contextual cues rather than surface meaning alone. Although Potentially Euphemistic Terms (PET)-based resources have been developed for several languages, Japanese euphemisms remain computationally unexplored despite their close interaction with honorifics, register variation, and orthographic choice. We introduce JP-PET, the first PET-based dataset for Japanese euphemism classification, comprising 1,672 annotated sentences across 101 PETs and ten semantic domains with register metadata. We evaluate two Japanese monolingual transformer models (Rinna RoBERTa and Tohoku BERT) and the multilingual XLM-R under three controlled PET-level data splits that isolate lexical familiarity and generalization to unseen euphemisms. While models achieve strong performance when PETs are shared between training and test data, performance drops substantially under PET-disjoint conditions, indicating reliance on lexical familiarity. Error analysis reveals systematic challenges in politically conventionalized expressions, metaphor-based euphemisms, and orthographic mitigation strategies. JP-PET provides the first benchmark for studying pragmatic meaning in Japanese NLP.
%R 10.63317/234ssv2bkqd2
%U https://aclanthology.org/2026.nonliteral-1.1/
%U https://doi.org/10.63317/234ssv2bkqd2
%P 1-11
Markdown (Informal)
[Challenges in Japanese Euphemism Classification: An Analysis of Pretrained Japanese and Multilingual Models](https://aclanthology.org/2026.nonliteral-1.1/) (Takahashi et al., NonLiteral 2026)
ACL