The First Surface Realisation Shared Task: Overview and Evaluation Results
The First Surface Realisation Shared Task: Overview and Evaluation Results
复制标题
DOI：
--
复制
发表时间：
2011-09
期刊：
影响因子：
--
通讯作者：
A. Belz;Michael White;Dominic Espinosa;Eric Kow;Deirdre Hogan;Amanda Stent
中科院分区：
文献类型：
--
作者：
A. Belz;Michael White;Dominic Espinosa;Eric Kow;Deirdre Hogan;Amanda Stent
表面实现(SR)任务是2011代挑战的一个新任务，有两个轨迹：(1)浅：从浅输入表征到实现的映射；(2)深：从深输入表征到实现的映射。五个团队总共提交了六个系统，我们还评估了人类背线。系统使用一系列内在指标进行自动评估。此外，人类评委在清晰度、可读性和含义相似性方面对系统进行了评估。此报告显示评估结果，以及对服务请求任务路径和评估方法的说明。有关参与系统的说明，请参阅本卷中紧跟在本结果报告之后的单独系统报告。
The Surface Realisation (SR) Task was a new task at Generation Challenges 2011, and had two tracks: (1) Shallow: mapping from shallow input representations to realisations; and (2) Deep: mapping from deep input representations to realisations. Five teams submitted six systems in total, and we additionally evaluated human toplines. Systems were evaluated automatically using a range of intrinsic metrics. In addition, systems were assessed by human judges in terms of Clarity, Readability and Meaning Similarity. This report presents the evaluation results, along with descriptions of the SR Task Tracks and evaluation methods. For descriptions of the participating systems, see the separate system reports in this volume, immediately following this results report.