Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene Hallucination

Hao Fei, Qian Liu, Meishan Zhang, Min Zhang, Tat-Seng Chua


Abstract
In this work, we investigate a more realistic unsupervised multimodal machine translation (UMMT) setup, inference-time image-free UMMT, where the model is trained with source-text image pairs, and tested with only source-text inputs. First, we represent the input images and texts with the visual and language scene graphs (SG), where such fine-grained vision-language features ensure a holistic understanding of the semantics. To enable pure-text input during inference, we devise a visual scene hallucination mechanism that dynamically generates pseudo visual SG from the given textual SG. Several SG-pivoting based learning objectives are introduced for unsupervised translation training. On the benchmark Multi30K data, our SG-based method outperforms the best-performing baseline by significant BLEU scores on the task and setup, helping yield translations with better completeness, relevance and fluency without relying on paired images. Further in-depth analyses reveal how our model advances in the task setting.
Anthology ID:
2023.acl-long.329
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:
5980–5994
Language:
URL:
https://aclanthology.org/2023.acl-long.329
DOI:
10.18653/v1/2023.acl-long.329
Bibkey:
Cite (ACL):
Hao Fei, Qian Liu, Meishan Zhang, Min Zhang, and Tat-Seng Chua. 2023. Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene Hallucination. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5980–5994, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene Hallucination (Fei et al., ACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2023.acl-long.329.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-5/2023.acl-long.329.mp4