@inproceedings{han-etal-2026-tchv,
title = "{TCHV}: Type-Conditioned Hypothesis Verification for Multimodal Named Entity Recognition",
author = "Han, Feiyu and
Liu, Yang and
Xu, Yongxiu and
Jiang, Yixiao and
Zhou, Zhaoqi and
Zhou, Chuan",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1945/",
pages = "41464--41483",
ISBN = "979-8-89176-462-0",
abstract = "Multimodal Named Entity Recognition (MNER) uses supplementary images to resolve ambiguity in entity mentions in noisy, short-form social-media text. Prevailing approaches typically fuse text with visually aligned features, but such cues often lack sufficient discriminative power and may support conflicting entity-type hypotheses. To address this issue, we propose TCHV, a lightweight framework grounded in a type-conditioned hypothesis-verification perspective. By formulating each span-type pair as a distinct hypothesis during inference, TCHV predicts the latent feature evidence expected under each hypothesis and validates it against observed multimodal representations through bidirectional text-image matching, using a visual relevance gate to suppress unin- formative images. Verification scores serve as surrogate evidence statistics; TCHV improves over established non-VLLM multimodal baselines on Twitter-2015/2017, and TCHV{\textdagger} leads the compared VLLM-based methods on Twitter-2017. Extensions demonstrate applicability to grounded and fine-grained settings. Code: https://github.com/ hanfeiyu703/ImaginE.git."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="han-etal-2026-tchv">
<titleInfo>
<title>TCHV: Type-Conditioned Hypothesis Verification for Multimodal Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Feiyu</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongxiu</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yixiao</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaoqi</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chuan</namePart>
<namePart type="family">Zhou</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Multimodal Named Entity Recognition (MNER) uses supplementary images to resolve ambiguity in entity mentions in noisy, short-form social-media text. Prevailing approaches typically fuse text with visually aligned features, but such cues often lack sufficient discriminative power and may support conflicting entity-type hypotheses. To address this issue, we propose TCHV, a lightweight framework grounded in a type-conditioned hypothesis-verification perspective. By formulating each span-type pair as a distinct hypothesis during inference, TCHV predicts the latent feature evidence expected under each hypothesis and validates it against observed multimodal representations through bidirectional text-image matching, using a visual relevance gate to suppress unin- formative images. Verification scores serve as surrogate evidence statistics; TCHV improves over established non-VLLM multimodal baselines on Twitter-2015/2017, and TCHV† leads the compared VLLM-based methods on Twitter-2017. Extensions demonstrate applicability to grounded and fine-grained settings. Code: https://github.com/ hanfeiyu703/ImaginE.git.</abstract>
<identifier type="citekey">han-etal-2026-tchv</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1945/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>41464</start>
<end>41483</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TCHV: Type-Conditioned Hypothesis Verification for Multimodal Named Entity Recognition
%A Han, Feiyu
%A Liu, Yang
%A Xu, Yongxiu
%A Jiang, Yixiao
%A Zhou, Zhaoqi
%A Zhou, Chuan
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F han-etal-2026-tchv
%X Multimodal Named Entity Recognition (MNER) uses supplementary images to resolve ambiguity in entity mentions in noisy, short-form social-media text. Prevailing approaches typically fuse text with visually aligned features, but such cues often lack sufficient discriminative power and may support conflicting entity-type hypotheses. To address this issue, we propose TCHV, a lightweight framework grounded in a type-conditioned hypothesis-verification perspective. By formulating each span-type pair as a distinct hypothesis during inference, TCHV predicts the latent feature evidence expected under each hypothesis and validates it against observed multimodal representations through bidirectional text-image matching, using a visual relevance gate to suppress unin- formative images. Verification scores serve as surrogate evidence statistics; TCHV improves over established non-VLLM multimodal baselines on Twitter-2015/2017, and TCHV† leads the compared VLLM-based methods on Twitter-2017. Extensions demonstrate applicability to grounded and fine-grained settings. Code: https://github.com/ hanfeiyu703/ImaginE.git.
%U https://aclanthology.org/2026.findings-emnlp.1945/
%P 41464-41483
Markdown (Informal)
[TCHV: Type-Conditioned Hypothesis Verification for Multimodal Named Entity Recognition](https://aclanthology.org/2026.findings-emnlp.1945/) (Han et al., Findings 2026)
ACL