A Visually-grounded First-person Dialogue Dataset with Verbal and Non-verbal Responses

Hisashi Kamezawa, Noriki Nishida, Nobuyuki Shimizu, Takashi Miyazaki, Hideki Nakayama


Abstract
In real-world dialogue, first-person visual information about where the other speakers are and what they are paying attention to is crucial to understand their intentions. Non-verbal responses also play an important role in social interactions. In this paper, we propose a visually-grounded first-person dialogue (VFD) dataset with verbal and non-verbal responses. The VFD dataset provides manually annotated (1) first-person images of agents, (2) utterances of human speakers, (3) eye-gaze locations of the speakers, and (4) the agents’ verbal and non-verbal responses. We present experimental results obtained using the proposed VFD dataset and recent neural network models (e.g., BERT, ResNet). The results demonstrate that first-person vision helps neural network models correctly understand human intentions, and the production of non-verbal responses is a challenging task like that of verbal responses. Our dataset is publicly available.
Anthology ID:
2020.emnlp-main.267
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3299–3310
Language:
URL:
https://www.aclweb.org/anthology/2020.emnlp-main.267
DOI:
10.18653/v1/2020.emnlp-main.267
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.emnlp-main.267.pdf