BriefGPT.xyz
Nov, 2022
文本到图像生成模型中的歧义消解：大象会飞吗？
Is the Elephant Flying? Resolving Ambiguities in Text-to-Image Generative Models
HTML
PDF
Ninareh Mehrabi, Palash Goyal, Apurv Verma, Jwala Dhamala, Varun Kumar...
TL;DR
研究在文本到图像生成模型中出现的歧义问题，通过建立基准数据集，提出一个框架来缓解这些问题，并通过自动和人工评估证明了这个框架的有效性。
Abstract
Natural language often contains
ambiguities
that can lead to misinterpretation and miscommunication. While humans can handle
ambiguities
effectively by asking clarifying questions and/or relying on contextual cue
→