Visual metaphors are powerful rhetorical devices used to persuade or
communicate creative ideas through images. Similar to linguistic metaphors,
they convey meaning implicitly through symbolism and juxtaposition of the
symbols. We propose a new task of generating visual metaphors from linguistic
metaphors. This is a challenging task for diffusion-based text-to-image models,
such as DALL$\cdot$E 2, since it requires the ability to model implicit meaning
and compositionality. We propose to solve the task through the collaboration
between Large Language Models (LLMs) and Diffusion Models: Instruct GPT-3
(davinci-002) with Chain-of-Thought prompting generates text that represents a
visual elaboration of the linguistic metaphor containing the implicit meaning
and relevant objects, which is then used as input to the diffusion-based
text-to-image models.Using a human-AI collaboration framework, where humans
interact both with the LLM and the top-performing diffusion model, we create a
high-quality dataset containing 6,476 visual metaphors for 1,540 linguistic
metaphors and their associated visual elaborations. Evaluation by professional
illustrators shows the promise of LLM-Diffusion Model collaboration for this
task.To evaluate the utility of our Human-AI collaboration framework and the
quality of our dataset, we perform both an intrinsic human-based evaluation and
an extrinsic evaluation using visual entailment as a downstream task.

本研究提出一种使用大型语言模型（LLM）与扩散模型的人工智能协作框架，旨在从语言隐喻中生成视觉隐喻，以便于传达含蓄含义并进行陈述。经过插图师的评估证明，这种协作模型的前景看好。

我发现一个隐喻：大型语言模型和扩散模型共同创造视觉隐喻

I Spy a Metaphor: Large Language Models and Diffusion Models Co-Create  Visual Metaphors

This paper reviews the historical development of AI and representative
philosophical thinking from the perspective of the research paradigm.
Additionally, it considers the methodology and applications of AI from a
philosophical perspective and anticipates its continued advancement. In the
history of AI, Symbolism and connectionism are the two main paradigms in AI
research. Symbolism holds that the world can be explained by symbols and dealt
with through precise, logical processes, but connectionism believes this
process should be implemented through artificial neural networks. Regardless of
how intelligent machines or programs should achieve their smart goals, the
historical development of AI demonstrates the best answer at this time. Still,
it is not the final answer of AI research.

本文从研究范式的角度回顾了人工智能技术和代表性的哲学思想的历史发展，并从哲学视角探讨了人工智能的方法论和应用，预期其不断进步。Symbolism 和 connectionism 是 AI 研究中的两个主要范式。本文指出，不管智能机器或程序如何实现其智能目标，人工智能的历史发展证明了当前最好的答案，但这并不是 AI 研究的最终答案.

人工智能与哲学的历史交互

A Historical Interaction between Artificial Intelligence and Philosophy

Emojis come with prepacked semantics making them great candidates to create
new forms of more accessible communications. Yet, little is known about how
much of this emojis semantic is agreed upon by humans, outside of textual
contexts. Thus, we collected a crowdsourced dataset of one-word emoji
descriptions for 1,289 emojis presented to participants with no surrounding
text. The emojis and their interpretations were then examined for ambiguity. We
find that with 30 annotations per emoji, 16 emojis (1.2%) are completely
unambiguous, whereas 55 emojis (4.3%) are so ambiguous that their descriptions
are indistinguishable from randomly chosen descriptions. Most of studied emojis
are spread out between the two extremes. Furthermore, investigating the
ambiguity of different types of emojis, we find that an important factor is the
extent to which an emoji has an embedded symbolical meaning drawn from an
established code-book of symbols. We conclude by discussing design
implications.

通过人们对 1289 个表情符号的一词式描述，探讨了表情符号的语义歧义情况以及其与符号学和设计的相关性。

关于表情符号的无上下文歧义性

On the Context-Free Ambiguity of Emoji

In order to convey the most content in their limited space, advertisements
embed references to outside knowledge via symbolism. For example, a motorcycle
stands for adventure (a positive property the ad wants associated with the
product being sold), and a gun stands for danger (a negative property to
dissuade viewers from undesirable behaviors). We show how to use symbolic
references to better understand the meaning of an ad. We further show how
anchoring ad understanding in general-purpose object recognition and image
captioning improves results. We formulate the ad understanding task as matching
the ad image to human-generated statements that describe the action that the ad
prompts, and the rationale it provides for taking this action. Our proposed
method outperforms the state of the art on this task, and on an alternative
formulation of question-answering on ads. We show additional applications of
our learned representations for matching ads to slogans, and clustering ads
according to their topic, without extra training.

本文介绍了如何利用符号引用来更好地理解广告，并将广告理解任务建模为将广告图像与人工生成的陈述匹配，提出的方法在广告理解任务以及问题回答方面均优于现有技术方法。此外，还展示了利用符号引用进行广告和标语匹配以及广告聚类分析的应用。