生成前度量：无需生成描述文本即可预测描述质量度量
神经与进化计算
2019-02-05 v1 计算与语言
摘要
图像描述生成系统通常针对参考输出进行评估。我们表明，基于神经模型赋予参考描述文本的概率，无需生成描述文本即可预测输出质量。此类生成前度量与标准评估度量高度相关。
引用
@article{arxiv.1810.05474,
title = {Pre-gen metrics: Predicting caption quality metrics without generating captions},
author = {Marc Tanti and Albert Gatt and Adrian Muscat},
journal= {arXiv preprint arXiv:1810.05474},
year = {2019}
}
备注
13 pages, 6 figures This publication will appear in the Proceedings of the First Workshop on Shortcomings in Vision and Language (2018). DOI to be inserted later