PhotoChat: A Human-Human Dialogue Dataset With Photo Sharing Behavior For Joint Image-Text Modeling

Xiaoxue Zang, Lijuan Liu, Maria Wang, Yang Song, Hao Zhang, Jindong Chen


Abstract
We present a new human-human dialogue dataset - PhotoChat, the first dataset that casts light on the photo sharing behavior in online messaging. PhotoChat contains 12k dialogues, each of which is paired with a user photo that is shared during the conversation. Based on this dataset, we propose two tasks to facilitate research on image-text modeling: a photo-sharing intent prediction task that predicts whether one intends to share a photo in the next conversation turn, and a photo retrieval task that retrieves the most relevant photo according to the dialogue context. In addition, for both tasks, we provide baseline models using the state-of-the-art models and report their benchmark performances. The best image retrieval model achieves 10.4% recall@1 (out of 1000 candidates) and the best photo intent prediction model achieves 58.1% F1 score, indicating that the dataset presents interesting yet challenging real-world problems. We are releasing PhotoChat to facilitate future research work among the community.
Anthology ID:
2021.acl-long.479
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6142–6152
Language:
URL:
https://aclanthology.org/2021.acl-long.479
DOI:
10.18653/v1/2021.acl-long.479
Bibkey:
Cite (ACL):
Xiaoxue Zang, Lijuan Liu, Maria Wang, Yang Song, Hao Zhang, and Jindong Chen. 2021. PhotoChat: A Human-Human Dialogue Dataset With Photo Sharing Behavior For Joint Image-Text Modeling. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 6142–6152, Online. Association for Computational Linguistics.
Cite (Informal):
PhotoChat: A Human-Human Dialogue Dataset With Photo Sharing Behavior For Joint Image-Text Modeling (Zang et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/2021.acl-long.479.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-2/2021.acl-long.479.mp4
Data
PhotoChatImage-ChatMS COCOVisual Question Answering