arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.04747cs.CL
收藏

风格迁移的人类评价研究综述

A Review of Human Evaluation for Style Transfer

University of Maryland(马里兰大学);Dataminr, Inc.(Dataminr公司)

Eleftheria Briakou, Sweta Agrawal, Ke Zhang, Joel Tetreault, Marine Carpuat

摘要:

本文回顾和总结了97篇风格迁移论文中描述的人类评估实践,涉及三个主要评估方面:风格迁移,意义保留和流畅性。原则上,人类评分员的评估应该是最可靠的。然而,在风格转移文件中,我们发现,人类评估的协议往往是不够详细和不标准化,这阻碍了在这一领域的研究的可重复性和进步,更好的人类和自动评估方法。

英文摘要:

This paper reviews and summarizes human evaluation practices described in 97 style transfer papers with respect to three main evaluation aspects: style transfer, meaning preservation, and fluency. In principle, evaluations by human raters should be the most reliable. However, in style transfer papers, we find that protocols for human evaluations are often underspecified and not standardized, which hampers the reproducibility of research in this field and progress toward better human and automatic evaluation methods.

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。

↑