@inproceedings{qin-anastasiu-2026-unimer,
title = "{U}ni{MER}: Multilingual Multimodal Emotion Recognition with Prototype-Guided Attention Pooling",
author = "Qin, Yinghua and
Anastasiu, David C.",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1611/",
pages = "36646--36659",
ISBN = "979-8-89176-459-0",
abstract = "Conversational emotion recognition suffers from two compounding limitations: models trained on imbalanced data report near-zero F1 on minority emotions, and evaluation has been almost exclusively English, leaving it unknown whether current methods generalize across languages. We propose UniMER, a parameter-efficient framework built on the insight that natural language is the universal interface: visual, acoustic, and facial cues are converted into text by a multimodal LLM, enabling a single LoRA-adapted backbone to process all modalities and languages through one shared representation. To prevent minority-class collapse under extreme imbalance, we introduce class-prototype attention pooling, which anchors each attention head to a learnable class prototype so every emotion retains dedicated representational capacity. With only 2.4{\%} trainable parameters, UniMER achieves state-of-the-art results on three benchmarks across three language families: MELD (English, +14.0pp macro F1), M3ED (Chinese, +3.2pp wF1, text-only), and AkaCE (Akan, +11.5pp macro F1), lifting AkaCE Fear and Disgust F1 from near-zero ($<$0.1{\%}) to 58{\%} and 40{\%}. All three benchmarks share the 7-class Ekman taxonomy, enabling direct cross-dataset transfer evaluation. Cross-lingual analysis reveals universal arousal-based confusions alongside culturally specific patterns: heightened neutral absorption in Chinese and prosodic confusion in Akan absent in English."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qin-anastasiu-2026-unimer">
<titleInfo>
<title>UniMER: Multilingual Multimodal Emotion Recognition with Prototype-Guided Attention Pooling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yinghua</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Anastasiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Conversational emotion recognition suffers from two compounding limitations: models trained on imbalanced data report near-zero F1 on minority emotions, and evaluation has been almost exclusively English, leaving it unknown whether current methods generalize across languages. We propose UniMER, a parameter-efficient framework built on the insight that natural language is the universal interface: visual, acoustic, and facial cues are converted into text by a multimodal LLM, enabling a single LoRA-adapted backbone to process all modalities and languages through one shared representation. To prevent minority-class collapse under extreme imbalance, we introduce class-prototype attention pooling, which anchors each attention head to a learnable class prototype so every emotion retains dedicated representational capacity. With only 2.4% trainable parameters, UniMER achieves state-of-the-art results on three benchmarks across three language families: MELD (English, +14.0pp macro F1), M3ED (Chinese, +3.2pp wF1, text-only), and AkaCE (Akan, +11.5pp macro F1), lifting AkaCE Fear and Disgust F1 from near-zero (<0.1%) to 58% and 40%. All three benchmarks share the 7-class Ekman taxonomy, enabling direct cross-dataset transfer evaluation. Cross-lingual analysis reveals universal arousal-based confusions alongside culturally specific patterns: heightened neutral absorption in Chinese and prosodic confusion in Akan absent in English.</abstract>
<identifier type="citekey">qin-anastasiu-2026-unimer</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1611/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>36646</start>
<end>36659</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UniMER: Multilingual Multimodal Emotion Recognition with Prototype-Guided Attention Pooling
%A Qin, Yinghua
%A Anastasiu, David C.
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F qin-anastasiu-2026-unimer
%X Conversational emotion recognition suffers from two compounding limitations: models trained on imbalanced data report near-zero F1 on minority emotions, and evaluation has been almost exclusively English, leaving it unknown whether current methods generalize across languages. We propose UniMER, a parameter-efficient framework built on the insight that natural language is the universal interface: visual, acoustic, and facial cues are converted into text by a multimodal LLM, enabling a single LoRA-adapted backbone to process all modalities and languages through one shared representation. To prevent minority-class collapse under extreme imbalance, we introduce class-prototype attention pooling, which anchors each attention head to a learnable class prototype so every emotion retains dedicated representational capacity. With only 2.4% trainable parameters, UniMER achieves state-of-the-art results on three benchmarks across three language families: MELD (English, +14.0pp macro F1), M3ED (Chinese, +3.2pp wF1, text-only), and AkaCE (Akan, +11.5pp macro F1), lifting AkaCE Fear and Disgust F1 from near-zero (<0.1%) to 58% and 40%. All three benchmarks share the 7-class Ekman taxonomy, enabling direct cross-dataset transfer evaluation. Cross-lingual analysis reveals universal arousal-based confusions alongside culturally specific patterns: heightened neutral absorption in Chinese and prosodic confusion in Akan absent in English.
%U https://aclanthology.org/2026.emnlp-main.1611/
%P 36646-36659
Markdown (Informal)
[UniMER: Multilingual Multimodal Emotion Recognition with Prototype-Guided Attention Pooling](https://aclanthology.org/2026.emnlp-main.1611/) (Qin & Anastasiu, EMNLP 2026)
ACL