@inproceedings{zare-etal-2026-ynwaaz,
title = "{YNWAAZ} at {S}em{E}val-2026 Task 1: Bridging the Semantic-Visual Gap: Multimodal Humor Generation",
author = "Zare, Mohammad Erfan and
Abbasi, Tahere and
Veisi, Hadi and
Ala, Sayin and
Naderi, Hanieh",
editor = "Kochmar, Ekaterina and
Ghosh, Debanjan and
North, Kai and
Komachi, Mamoru",
booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.semeval-1.171/",
pages = "1308--1318",
ISBN = "979-8-89176-414-9",
abstract = "Developing Computational Humor systems at a multilingual and multimodal scale requires transcending simple text generation paradigms to focus on intent and context understanding. In this study, we address two key limitations in Foundation Models:Association Failure in textual tasks, which prevents the formation of coherent semantic links between incongruous concepts, and Temporal Blindness in video processing, which disrupts narrative comprehension. To tackle these challenges, we propose a unified architecture comprising an Intent-Aware RAG system for mitigating linguistic gaps across English, Spanish, and Chinese, and a Cascaded Visual Perception pipeline for modeling the narrative structure of video content. A key innovation of this work is the utilization of small language models (TinyLlama) as a SemanticDenoise Filter, converting noisy visual signals into structured, coherent textual representations. Experimental results demonstrate that this modular architecture reduces cultural-semantic gaps in certain languages and produces outputs that generally align better with human humor preferences, though highly nuanced languages still present a challenge."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zare-etal-2026-ynwaaz">
<titleInfo>
<title>YNWAAZ at SemEval-2026 Task 1: Bridging the Semantic-Visual Gap: Multimodal Humor Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Erfan</namePart>
<namePart type="family">Zare</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tahere</namePart>
<namePart type="family">Abbasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hadi</namePart>
<namePart type="family">Veisi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sayin</namePart>
<namePart type="family">Ala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanieh</namePart>
<namePart type="family">Naderi</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 20th International Workshop on Semantic Evaluation (2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</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">979-8-89176-414-9</identifier>
</relatedItem>
<abstract>Developing Computational Humor systems at a multilingual and multimodal scale requires transcending simple text generation paradigms to focus on intent and context understanding. In this study, we address two key limitations in Foundation Models:Association Failure in textual tasks, which prevents the formation of coherent semantic links between incongruous concepts, and Temporal Blindness in video processing, which disrupts narrative comprehension. To tackle these challenges, we propose a unified architecture comprising an Intent-Aware RAG system for mitigating linguistic gaps across English, Spanish, and Chinese, and a Cascaded Visual Perception pipeline for modeling the narrative structure of video content. A key innovation of this work is the utilization of small language models (TinyLlama) as a SemanticDenoise Filter, converting noisy visual signals into structured, coherent textual representations. Experimental results demonstrate that this modular architecture reduces cultural-semantic gaps in certain languages and produces outputs that generally align better with human humor preferences, though highly nuanced languages still present a challenge.</abstract>
<identifier type="citekey">zare-etal-2026-ynwaaz</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.171/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1308</start>
<end>1318</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T YNWAAZ at SemEval-2026 Task 1: Bridging the Semantic-Visual Gap: Multimodal Humor Generation
%A Zare, Mohammad Erfan
%A Abbasi, Tahere
%A Veisi, Hadi
%A Ala, Sayin
%A Naderi, Hanieh
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F zare-etal-2026-ynwaaz
%X Developing Computational Humor systems at a multilingual and multimodal scale requires transcending simple text generation paradigms to focus on intent and context understanding. In this study, we address two key limitations in Foundation Models:Association Failure in textual tasks, which prevents the formation of coherent semantic links between incongruous concepts, and Temporal Blindness in video processing, which disrupts narrative comprehension. To tackle these challenges, we propose a unified architecture comprising an Intent-Aware RAG system for mitigating linguistic gaps across English, Spanish, and Chinese, and a Cascaded Visual Perception pipeline for modeling the narrative structure of video content. A key innovation of this work is the utilization of small language models (TinyLlama) as a SemanticDenoise Filter, converting noisy visual signals into structured, coherent textual representations. Experimental results demonstrate that this modular architecture reduces cultural-semantic gaps in certain languages and produces outputs that generally align better with human humor preferences, though highly nuanced languages still present a challenge.
%U https://aclanthology.org/2026.semeval-1.171/
%P 1308-1318
Markdown (Informal)
[YNWAAZ at SemEval-2026 Task 1: Bridging the Semantic-Visual Gap: Multimodal Humor Generation](https://aclanthology.org/2026.semeval-1.171/) (Zare et al., SemEval 2026)
ACL