3AM: An Ambiguity-Aware Multi-Modal Machine Translation Dataset

arXiv:2404.18413v1 Announce Type: new
Abstract: Multimodal machine translation (MMT) is a challenging task that seeks to improve translation quality by incorporating visual information. However, recent studies have indicated that the visual information provided by existing MMT datasets is insufficient, causing models to disregard it and overestimate their capabilities. This issue presents a significant obstacle to the development of MMT research. This paper presents a novel solution to this issue by introducing 3AM, an ambiguity-aware MMT dataset comprising 26,000 parallel sentence …

arxiv cs.ai cs.cv dataset machine machine translation modal multi-modal translation type