arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2004.06814cs.CL
收藏

AMR到英语生成系统的人类评估

A Human Evaluation of AMR-to-English Generation Systems

Georgetown University(乔治城大学)

Emma Manning, Shira Wein, Nathan Schneider

摘要:

用于从抽象意义表示(AMR)生成英语文本的大多数当前最先进的系统仅使用自动化度量(诸如BLEU)来评估,已知自动化度量对于自然语言生成是有问题的。在这项工作中,我们提出了一个新的人类评估的结果,收集流畅性和充分的分数,以及分类的错误类型,最近的AMR生成系统。我们讨论了这些系统的相对质量,以及我们的结果与自动指标的比较,发现虽然指标在整体排名系统中大多是成功的,但收集人类判断可以进行更细致的比较。我们还分析了这些系统所犯的常见错误。

英文摘要:

Most current state-of-the art systems for generating English text from Abstract Meaning Representation (AMR) have been evaluated only using automated metrics, such as BLEU, which are known to be problematic for natural language generation. In this work, we present the results of a new human evaluation which collects fluency and adequacy scores, as well as categorization of error types, for several recent AMR generation systems. We discuss the relative quality of these systems and how our results compare to those of automatic metrics, finding that while the metrics are mostly successful in ranking systems overall, collecting human judgments allows for more nuanced comparisons. We also analyze common errors made by these systems.

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。

↑