@inproceedings{jang-etal-2025-enabling,
title = "Enabling Chatbots with Eyes and Ears: An Immersive Multimodal Conversation System for Dynamic Interactions",
author = {Jang, Jihyoung and
Bae, Minwook and
Kim, Minji and
Hakkani-T{\"u}r, Dilek and
Kim, Hyounghun},
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.1519/",
doi = "10.18653/v1/2025.acl-long.1519",
pages = "31481--31512",
ISBN = "979-8-89176-251-0",
abstract = "As chatbots continue to evolve toward human-like, real-world, interactions, multimodality remains an active area of research and exploration. So far, efforts to integrate multimodality into chatbots have primarily focused on image-centric tasks, such as visual dialogue and image-based instructions, placing emphasis on the ``eyes'' of human perception while neglecting the ``ears'', namely auditory aspects. Moreover, these studies often center around static interactions that focus on discussing the modality rather than naturally incorporating it into the conversation, which limits the richness of simultaneous, dynamic engagement. Furthermore, while multimodality has been explored in multi-party and multi-session conversations, task-specific constraints have hindered its seamless integration into dynamic, natural conversations. To address these challenges, this study aims to equip chatbots with ``eyes and ears'' capable of more immersive interactions with humans. As part of this effort, we introduce a new multimodal conversation dataset, Multimodal Multi-Session Multi-Party Conversation ($M^3C$), and propose a novel multimodal conversation model featuring multimodal memory retrieval. Our model, trained on the $M^3C$, demonstrates the ability to seamlessly engage in long-term conversations with multiple speakers in complex, real-world-like settings, effectively processing visual and auditory inputs to understand and respond appropriately. Human evaluations highlight the model{'}s strong performance in maintaining coherent and dynamic interactions, demonstrating its potential for advanced multimodal conversational agents."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jang-etal-2025-enabling">
<titleInfo>
<title>Enabling Chatbots with Eyes and Ears: An Immersive Multimodal Conversation System for Dynamic Interactions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jihyoung</namePart>
<namePart type="family">Jang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minwook</namePart>
<namePart type="family">Bae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minji</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tür</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyounghun</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>As chatbots continue to evolve toward human-like, real-world, interactions, multimodality remains an active area of research and exploration. So far, efforts to integrate multimodality into chatbots have primarily focused on image-centric tasks, such as visual dialogue and image-based instructions, placing emphasis on the “eyes” of human perception while neglecting the “ears”, namely auditory aspects. Moreover, these studies often center around static interactions that focus on discussing the modality rather than naturally incorporating it into the conversation, which limits the richness of simultaneous, dynamic engagement. Furthermore, while multimodality has been explored in multi-party and multi-session conversations, task-specific constraints have hindered its seamless integration into dynamic, natural conversations. To address these challenges, this study aims to equip chatbots with “eyes and ears” capable of more immersive interactions with humans. As part of this effort, we introduce a new multimodal conversation dataset, Multimodal Multi-Session Multi-Party Conversation (M³C), and propose a novel multimodal conversation model featuring multimodal memory retrieval. Our model, trained on the M³C, demonstrates the ability to seamlessly engage in long-term conversations with multiple speakers in complex, real-world-like settings, effectively processing visual and auditory inputs to understand and respond appropriately. Human evaluations highlight the model’s strong performance in maintaining coherent and dynamic interactions, demonstrating its potential for advanced multimodal conversational agents.</abstract>
<identifier type="citekey">jang-etal-2025-enabling</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.1519</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.1519/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>31481</start>
<end>31512</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enabling Chatbots with Eyes and Ears: An Immersive Multimodal Conversation System for Dynamic Interactions
%A Jang, Jihyoung
%A Bae, Minwook
%A Kim, Minji
%A Hakkani-Tür, Dilek
%A Kim, Hyounghun
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F jang-etal-2025-enabling
%X As chatbots continue to evolve toward human-like, real-world, interactions, multimodality remains an active area of research and exploration. So far, efforts to integrate multimodality into chatbots have primarily focused on image-centric tasks, such as visual dialogue and image-based instructions, placing emphasis on the “eyes” of human perception while neglecting the “ears”, namely auditory aspects. Moreover, these studies often center around static interactions that focus on discussing the modality rather than naturally incorporating it into the conversation, which limits the richness of simultaneous, dynamic engagement. Furthermore, while multimodality has been explored in multi-party and multi-session conversations, task-specific constraints have hindered its seamless integration into dynamic, natural conversations. To address these challenges, this study aims to equip chatbots with “eyes and ears” capable of more immersive interactions with humans. As part of this effort, we introduce a new multimodal conversation dataset, Multimodal Multi-Session Multi-Party Conversation (M³C), and propose a novel multimodal conversation model featuring multimodal memory retrieval. Our model, trained on the M³C, demonstrates the ability to seamlessly engage in long-term conversations with multiple speakers in complex, real-world-like settings, effectively processing visual and auditory inputs to understand and respond appropriately. Human evaluations highlight the model’s strong performance in maintaining coherent and dynamic interactions, demonstrating its potential for advanced multimodal conversational agents.
%R 10.18653/v1/2025.acl-long.1519
%U https://aclanthology.org/2025.acl-long.1519/
%U https://doi.org/10.18653/v1/2025.acl-long.1519
%P 31481-31512
Markdown (Informal)
[Enabling Chatbots with Eyes and Ears: An Immersive Multimodal Conversation System for Dynamic Interactions](https://aclanthology.org/2025.acl-long.1519/) (Jang et al., ACL 2025)
ACL