arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.00619cs.CLcs.CV
收藏

用可视化表示探索上下文语言模型的共同点

Probing Contextual Language Models for Common Ground with Visual Representations

Paul G. Allen School of Computer Science & Engineering(保罗·G·艾伦计算机科学与工程学院);University of Washington(华盛顿大学)

Gabriel Ilharco, Rowan Zellers, Ali Farhadi, Hannaneh Hajishirzi

摘要:

大规模上下文语言模型的成功吸引了人们对探索其表示中编码的内容的极大兴趣。在这项工作中,我们考虑了一个新的问题:在何种程度上具体名词的上下文表示与相应的视觉表示对齐?我们设计了一个探测模型,评估如何有效地区分匹配和不匹配的视觉表示的纯文本表示。我们的研究结果表明,语言表征本身提供了一个强有力的信号,从正确的对象类别检索图像补丁。此外,他们是有效的检索图像补丁的特定实例,文本上下文在这个过程中起着重要的作用。基于视觉的语言模型在实例检索方面略优于纯文本的语言模型,但大大低于人类。我们希望我们的分析启发未来的研究在理解和提高语言模型的视觉能力。

英文摘要:

The success of large-scale contextual language models has attracted great interest in probing what is encoded in their representations. In this work, we consider a new question: to what extent contextual representations of concrete nouns are aligned with corresponding visual representations? We design a probing model that evaluates how effective are text-only representations in distinguishing between matching and non-matching visual representations. Our findings show that language representations alone provide a strong signal for retrieving image patches from the correct object categories. Moreover, they are effective in retrieving specific instances of image patches; textual context plays an important role in this process. Visually grounded language models slightly outperform text-only language models in instance retrieval, but greatly under-perform humans. We hope our analyses inspire future research in understanding and improving the visual capabilities of language models.

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。

↑