J-CRe3: A Japanese Conversation Dataset for Real-world Reference Resolution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ueda, Nobuhiro, Habe, Hideko, Matsui, Yoko, Yuguchi, Akishige, Kawano, Seiya, Kawanishi, Yasutomo, Kurohashi, Sadao, Yoshino, Koichiro
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916182590750720
author Ueda, Nobuhiro
Habe, Hideko
Matsui, Yoko
Yuguchi, Akishige
Kawano, Seiya
Kawanishi, Yasutomo
Kurohashi, Sadao
Yoshino, Koichiro
author_facet Ueda, Nobuhiro
Habe, Hideko
Matsui, Yoko
Yuguchi, Akishige
Kawano, Seiya
Kawanishi, Yasutomo
Kurohashi, Sadao
Yoshino, Koichiro
contents Understanding expressions that refer to the physical world is crucial for such human-assisting systems in the real world, as robots that must perform actions that are expected by users. In real-world reference resolution, a system must ground the verbal information that appears in user interactions to the visual information observed in egocentric views. To this end, we propose a multimodal reference resolution task and construct a Japanese Conversation dataset for Real-world Reference Resolution (J-CRe3). Our dataset contains egocentric video and dialogue audio of real-world conversations between two people acting as a master and an assistant robot at home. The dataset is annotated with crossmodal tags between phrases in the utterances and the object bounding boxes in the video frames. These tags include indirect reference relations, such as predicate-argument structures and bridging references as well as direct reference relations. We also constructed an experimental model and clarified the challenges in multimodal reference resolution tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2403_19259
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle J-CRe3: A Japanese Conversation Dataset for Real-world Reference Resolution
Ueda, Nobuhiro
Habe, Hideko
Matsui, Yoko
Yuguchi, Akishige
Kawano, Seiya
Kawanishi, Yasutomo
Kurohashi, Sadao
Yoshino, Koichiro
Computation and Language
Understanding expressions that refer to the physical world is crucial for such human-assisting systems in the real world, as robots that must perform actions that are expected by users. In real-world reference resolution, a system must ground the verbal information that appears in user interactions to the visual information observed in egocentric views. To this end, we propose a multimodal reference resolution task and construct a Japanese Conversation dataset for Real-world Reference Resolution (J-CRe3). Our dataset contains egocentric video and dialogue audio of real-world conversations between two people acting as a master and an assistant robot at home. The dataset is annotated with crossmodal tags between phrases in the utterances and the object bounding boxes in the video frames. These tags include indirect reference relations, such as predicate-argument structures and bridging references as well as direct reference relations. We also constructed an experimental model and clarified the challenges in multimodal reference resolution tasks.
title J-CRe3: A Japanese Conversation Dataset for Real-world Reference Resolution
topic Computation and Language
url https://arxiv.org/abs/2403.19259