Visual Information Guided Zero-Shot Paraphrase Generation

Zhe Lin, Xiaojun Wan


Abstract
Zero-shot paraphrase generation has drawn much attention as the large-scale high-quality paraphrase corpus is limited. Back-translation, also known as the pivot-based method, is typical to this end. Several works leverage different information as ”pivot” such as language, semantic representation and so on. In this paper, we explore using visual information such as image as the ”pivot” of back-translation. Different with the pipeline back-translation method, we propose visual information guided zero-shot paraphrase generation (ViPG) based only on paired image-caption data. It jointly trains an image captioning model and a paraphrasing model and leverage the image captioning model to guide the training of the paraphrasing model. Both automatic evaluation and human evaluation show our model can generate paraphrase with good relevancy, fluency and diversity, and image is a promising kind of pivot for zero-shot paraphrase generation.
Anthology ID:
2022.coling-1.568
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
6530–6539
Language:
URL:
https://aclanthology.org/2022.coling-1.568
DOI:
Bibkey:
Cite (ACL):
Zhe Lin and Xiaojun Wan. 2022. Visual Information Guided Zero-Shot Paraphrase Generation. In Proceedings of the 29th International Conference on Computational Linguistics, pages 6530–6539, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Visual Information Guided Zero-Shot Paraphrase Generation (Lin & Wan, COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.568.pdf