arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.12256cs.CL

以场景图为枢轴:基于视觉场景幻觉的推理时无图像无监督多模态机器翻译

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

National University of Singapore(新加坡国立大学);Nanyang Technological University(南洋理工大学);Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳))

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

AI总结:

本文提出以场景图为枢轴的无监督多模态机器翻译方法,通过视觉场景幻觉机制在推理时从文本场景图生成伪视觉场景图,在Multi30K上显著超越基线BLEU分数。

摘要:

在这项工作中,我们研究了一种更贴近现实的无监督多模态机器翻译(UMMT)设置,即推理时无图像UMMT,其中模型使用源文本-图像对进行训练,而测试时仅使用源文本输入。首先,我们使用视觉场景图和语言场景图(SG)来表示输入图像和文本,这种细粒度的视觉-语言特征确保了对语义的整体理解。为了使推理时能够使用纯文本输入,我们设计了一种视觉场景幻觉机制,该机制根据给定的文本场景图动态生成伪视觉场景图。我们引入了若干基于场景图枢轴(SG-pivoting)的学习目标用于无监督翻译训练。在基准数据集Multi30K上,我们基于场景图的方法在该任务和设置下以显著的BLEU分数超越了表现最佳的基线,有助于在不依赖配对图像的情况下生成具有更好完整性、相关性和流畅性的翻译。进一步的深入分析揭示了我们的模型在该任务设置中如何取得进展。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑