@inproceedings{bhansali-etal-2026-memebuddy,
title = "{M}eme{B}uddy: Dialog-Style Audio Representations for Engaging Non-Visual Meme Experiences",
author = "Bhansali, Chirag and
Ashok, Vikas and
Lee, Hae-Na",
editor = "Choi, Jinho D. and
Chen, Yun-Nung and
Funakoshi, Kotaro and
Emami, Ali",
booktitle = "Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = aug,
year = "2026",
address = "Atlanta, Georgia, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.sigdial-1.46/",
pages = "649--667",
abstract = "Image memes are a pervasive form of online communication, widely used to convey humor, opinions, and cultural references. Prior work has explored making memes accessible to blind users, primarily through auto-generated descriptive captions. While these approaches improve comprehensibility and sometimes incorporate prosodic or emotional cues, they often fail to capture the humor, narrative structure, and contextual nuances that make memes engaging. We present MemeBuddy, a system that models memes as dialog, generating structured, multi-turn audio representations using role-based speakers. MemeBuddy reinterprets a meme as a conversation between two speakers, integrating extracted meme text with contextual knowledge implicitly inferred by a multimodal LLM (e.g., recognition of common meme templates and cultural references) to convey intent, timing, and implicit meaning through conversational interaction. We evaluate MemeBuddy in a user study with 14 blind participants. Results show that dialog-style meme representations consistently improve engagement and user satisfaction compared to caption-style descriptions, while maintaining comparable comprehension."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhansali-etal-2026-memebuddy">
<titleInfo>
<title>MemeBuddy: Dialog-Style Audio Representations for Engaging Non-Visual Meme Experiences</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chirag</namePart>
<namePart type="family">Bhansali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vikas</namePart>
<namePart type="family">Ashok</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hae-Na</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinho</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kotaro</namePart>
<namePart type="family">Funakoshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Emami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Atlanta, Georgia, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Image memes are a pervasive form of online communication, widely used to convey humor, opinions, and cultural references. Prior work has explored making memes accessible to blind users, primarily through auto-generated descriptive captions. While these approaches improve comprehensibility and sometimes incorporate prosodic or emotional cues, they often fail to capture the humor, narrative structure, and contextual nuances that make memes engaging. We present MemeBuddy, a system that models memes as dialog, generating structured, multi-turn audio representations using role-based speakers. MemeBuddy reinterprets a meme as a conversation between two speakers, integrating extracted meme text with contextual knowledge implicitly inferred by a multimodal LLM (e.g., recognition of common meme templates and cultural references) to convey intent, timing, and implicit meaning through conversational interaction. We evaluate MemeBuddy in a user study with 14 blind participants. Results show that dialog-style meme representations consistently improve engagement and user satisfaction compared to caption-style descriptions, while maintaining comparable comprehension.</abstract>
<identifier type="citekey">bhansali-etal-2026-memebuddy</identifier>
<location>
<url>https://aclanthology.org/2026.sigdial-1.46/</url>
</location>
<part>
<date>2026-08</date>
<extent unit="page">
<start>649</start>
<end>667</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MemeBuddy: Dialog-Style Audio Representations for Engaging Non-Visual Meme Experiences
%A Bhansali, Chirag
%A Ashok, Vikas
%A Lee, Hae-Na
%Y Choi, Jinho D.
%Y Chen, Yun-Nung
%Y Funakoshi, Kotaro
%Y Emami, Ali
%S Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2026
%8 August
%I Association for Computational Linguistics
%C Atlanta, Georgia, USA
%F bhansali-etal-2026-memebuddy
%X Image memes are a pervasive form of online communication, widely used to convey humor, opinions, and cultural references. Prior work has explored making memes accessible to blind users, primarily through auto-generated descriptive captions. While these approaches improve comprehensibility and sometimes incorporate prosodic or emotional cues, they often fail to capture the humor, narrative structure, and contextual nuances that make memes engaging. We present MemeBuddy, a system that models memes as dialog, generating structured, multi-turn audio representations using role-based speakers. MemeBuddy reinterprets a meme as a conversation between two speakers, integrating extracted meme text with contextual knowledge implicitly inferred by a multimodal LLM (e.g., recognition of common meme templates and cultural references) to convey intent, timing, and implicit meaning through conversational interaction. We evaluate MemeBuddy in a user study with 14 blind participants. Results show that dialog-style meme representations consistently improve engagement and user satisfaction compared to caption-style descriptions, while maintaining comparable comprehension.
%U https://aclanthology.org/2026.sigdial-1.46/
%P 649-667
Markdown (Informal)
[MemeBuddy: Dialog-Style Audio Representations for Engaging Non-Visual Meme Experiences](https://aclanthology.org/2026.sigdial-1.46/) (Bhansali et al., SIGDIAL 2026)
ACL