On Vision Features in Multimodal Machine Translation

By Bei Li, Chuanhao Lv, Zefan Zhou, Tao Zhou, Tong Xiao, Anxiang Ma, Jingbo Zhu. 2022

85 citations recorded by the source corpus.

Previous work on multimodal machine translation (MMT) has focused on the way of incorporating vision features into translation but little attention is on the quality of vision models. In this work, we investigate the impact of vision models on MMT. Given the fact that Transformer is becoming popular in computer vision, we experiment with various strong models (such as Vision Transformer) and enhanced features (such as object-detection and image captioning). We develop a selective attention model to study the patch-level contribution of an image in MMT. On detailed probing tasks, we find that stronger vision models are helpful for learning translation from the visual modality. Our results also suggest the need of carefully examining MMT models, especially when current benchmarks are small-scale and biased.

Subfields: Multimodal Learning, Machine Translation

Citations in the corpus

• Multimodal Chain-of-Thought Reasoning in Language Models (2023, neutral): “After obtaining the patch-level vision features, we apply a learnable projection matrix W h to convert the shape of VisionExtractor ( X vision ) into that of H language ; thus we have H vision ∈ R m × d where m is the number of patches.”