Abstract
There are common semantics shared across text and images. Given a sentence in a source language, whether depicting the visual scene helps translation into a target language? Existing multimodal neural machine translation methods (MNMT) require triplets of bilingual sentence - image for training and tuples of source sentence - image for inference. In this paper, we propose ImagiT, a novel machine translation method via visual imagination. ImagiT first learns to generate visual representation from the source sentence, and then utilizes both source sentence and the “imagined representation” to produce a target translation. Unlike previous methods, it only needs the source sentence at the inference time. Experiments demonstrate that ImagiT benefits from visual imagination and significantly outperforms the text-only neural machine translation baselines. Further analysis reveals that the imagination process in ImagiT helps fill in missing information when performing the degradation strategy.- Anthology ID:
- 2021.naacl-main.457
- Volume:
- Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Month:
- June
- Year:
- 2021
- Address:
- Online
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5738–5748
- Language:
- URL:
- https://aclanthology.org/2021.naacl-main.457
- DOI:
- 10.18653/v1/2021.naacl-main.457
- Cite (ACL):
- Quanyu Long, Mingxuan Wang, and Lei Li. 2021. Generative Imagination Elevates Machine Translation. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5738–5748, Online. Association for Computational Linguistics.
- Cite (Informal):
- Generative Imagination Elevates Machine Translation (Long et al., NAACL 2021)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2021.naacl-main.457.pdf
- Data
- COCO, Flickr30k