Cross2StrA: Unpaired Cross-lingual Image Captioning with Cross-lingual Cross-modal Structure-pivoted Alignment

Shengqiong Wu, Hao Fei, Wei Ji, Tat-Seng Chua


Abstract
Unpaired cross-lingual image captioning has long suffered from irrelevancy and disfluency issues, due to the inconsistencies of the semantic scene and syntax attributes during transfer. In this work, we propose to address the above problems by incorporating the scene graph (SG) structures and the syntactic constituency (SC) trees. Our captioner contains the semantic structure-guided image-to-pivot captioning and the syntactic structure-guided pivot-to-target translation, two of which are joined via pivot language. We then take the SG and SC structures as pivoting, performing cross-modal semantic structure alignment and cross-lingual syntactic structure alignment learning. We further introduce cross-lingual&cross-modal back-translation training to fully align the captioning and translation stages. Experiments on English-Chinese transfers show that our model shows great superiority in improving captioning relevancy and fluency.
Anthology ID:
2023.acl-long.146
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2593–2608
Language:
URL:
https://aclanthology.org/2023.acl-long.146
DOI:
10.18653/v1/2023.acl-long.146
Bibkey:
Cite (ACL):
Shengqiong Wu, Hao Fei, Wei Ji, and Tat-Seng Chua. 2023. Cross2StrA: Unpaired Cross-lingual Image Captioning with Cross-lingual Cross-modal Structure-pivoted Alignment. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2593–2608, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Cross2StrA: Unpaired Cross-lingual Image Captioning with Cross-lingual Cross-modal Structure-pivoted Alignment (Wu et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-long.146.pdf
Video:
 https://aclanthology.org/2023.acl-long.146.mp4