@inproceedings{bisht-etal-2026-multimodal,
title = "Multimodal Code-Mixed {H}indi-{E}nglish Dataset For Humor Recognition in Conversations",
author = "Bisht, Abhishek Singh and
Kumar, Rakesh and
Chaturvedi, Amrita",
editor = "Ghaleb, Esam and
Takmaz, Ece and
Frassinelli, Diego and
Khaertdinov, Bulat and
Fern{\'a}ndez, Raquel and
Yumak, Zerrin and
Ozyurek, Asli",
booktitle = "Proceedings of the 1st Workshop on Multimodal Interaction in Face-to-Face Dialogue",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.mint-1.4/",
pages = "33--39",
ISBN = "979-8-89176-482-8",
abstract = "Humor recognition in conversations is a highly challenging task due to its reliance on context, sarcasm, timing, and multimodal cues. While several humour datasets exist for English, resources for Indic languages like Hindi remain little scarce, limiting the development of culturally aware conversational AI systems. To address this gap, we introduce a new multimodal dataset for humour detection from conversational dialogues. The dataset consists of 5203 annotated utterances of 2 season containing 8 episodes each from a popular Indian web series Panchayat. Utterances are kept in their original Devanagari script as spoken in the series, without transliteration or standardization into pure Hindi, to retain the natural conversational tone and cultural nuances. Each utterance is annotated with a binary humour label (Humour / Not Humour) and includes aligned textual, acoustic and visual information, making it suitable for multimodal and context-aware humour research. Our experiments highlight the complementary nature of multimodal signals and the importance of conversational context in understanding Hindi humour. This dataset is expected to promote research on computational humour, sarcasm detection and multimodal dialogue understanding for low-resource languages. The dataset and baselines are available at https://huggingface.co/datasets/Abhis4e/Panchayat-multimodal-dataset and https://github.com/singhbishtabhishek/Multimodal-Dataset."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bisht-etal-2026-multimodal">
<titleInfo>
<title>Multimodal Code-Mixed Hindi-English Dataset For Humor Recognition in Conversations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abhishek</namePart>
<namePart type="given">Singh</namePart>
<namePart type="family">Bisht</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rakesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amrita</namePart>
<namePart type="family">Chaturvedi</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 1st Workshop on Multimodal Interaction in Face-to-Face Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Esam</namePart>
<namePart type="family">Ghaleb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ece</namePart>
<namePart type="family">Takmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diego</namePart>
<namePart type="family">Frassinelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bulat</namePart>
<namePart type="family">Khaertdinov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raquel</namePart>
<namePart type="family">Fernández</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zerrin</namePart>
<namePart type="family">Yumak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asli</namePart>
<namePart type="family">Ozyurek</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">979-8-89176-482-8</identifier>
</relatedItem>
<abstract>Humor recognition in conversations is a highly challenging task due to its reliance on context, sarcasm, timing, and multimodal cues. While several humour datasets exist for English, resources for Indic languages like Hindi remain little scarce, limiting the development of culturally aware conversational AI systems. To address this gap, we introduce a new multimodal dataset for humour detection from conversational dialogues. The dataset consists of 5203 annotated utterances of 2 season containing 8 episodes each from a popular Indian web series Panchayat. Utterances are kept in their original Devanagari script as spoken in the series, without transliteration or standardization into pure Hindi, to retain the natural conversational tone and cultural nuances. Each utterance is annotated with a binary humour label (Humour / Not Humour) and includes aligned textual, acoustic and visual information, making it suitable for multimodal and context-aware humour research. Our experiments highlight the complementary nature of multimodal signals and the importance of conversational context in understanding Hindi humour. This dataset is expected to promote research on computational humour, sarcasm detection and multimodal dialogue understanding for low-resource languages. The dataset and baselines are available at https://huggingface.co/datasets/Abhis4e/Panchayat-multimodal-dataset and https://github.com/singhbishtabhishek/Multimodal-Dataset.</abstract>
<identifier type="citekey">bisht-etal-2026-multimodal</identifier>
<location>
<url>https://aclanthology.org/2026.mint-1.4/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>33</start>
<end>39</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multimodal Code-Mixed Hindi-English Dataset For Humor Recognition in Conversations
%A Bisht, Abhishek Singh
%A Kumar, Rakesh
%A Chaturvedi, Amrita
%Y Ghaleb, Esam
%Y Takmaz, Ece
%Y Frassinelli, Diego
%Y Khaertdinov, Bulat
%Y Fernández, Raquel
%Y Yumak, Zerrin
%Y Ozyurek, Asli
%S Proceedings of the 1st Workshop on Multimodal Interaction in Face-to-Face Dialogue
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-482-8
%F bisht-etal-2026-multimodal
%X Humor recognition in conversations is a highly challenging task due to its reliance on context, sarcasm, timing, and multimodal cues. While several humour datasets exist for English, resources for Indic languages like Hindi remain little scarce, limiting the development of culturally aware conversational AI systems. To address this gap, we introduce a new multimodal dataset for humour detection from conversational dialogues. The dataset consists of 5203 annotated utterances of 2 season containing 8 episodes each from a popular Indian web series Panchayat. Utterances are kept in their original Devanagari script as spoken in the series, without transliteration or standardization into pure Hindi, to retain the natural conversational tone and cultural nuances. Each utterance is annotated with a binary humour label (Humour / Not Humour) and includes aligned textual, acoustic and visual information, making it suitable for multimodal and context-aware humour research. Our experiments highlight the complementary nature of multimodal signals and the importance of conversational context in understanding Hindi humour. This dataset is expected to promote research on computational humour, sarcasm detection and multimodal dialogue understanding for low-resource languages. The dataset and baselines are available at https://huggingface.co/datasets/Abhis4e/Panchayat-multimodal-dataset and https://github.com/singhbishtabhishek/Multimodal-Dataset.
%U https://aclanthology.org/2026.mint-1.4/
%P 33-39
Markdown (Informal)
[Multimodal Code-Mixed Hindi-English Dataset For Humor Recognition in Conversations](https://aclanthology.org/2026.mint-1.4/) (Bisht et al., MINT 2026)
ACL