A Proposal for Task-based Evaluation of Text Summarization Systems
A Proposal for Task-based Evaluation of Text Summarization Systems
复制标题
基于任务的文本摘要系统评估提案
DOI：
--
复制
发表时间：
1997
期刊：
影响因子：
--
通讯作者：
Therese Firmin Hand
中科院分区：
文献类型：
--
作者：
Therese Firmin Hand
评估是任何研究和开发工作的关键部分，但评估的目标和重点往往是狭窄的范围，针对特定的算法或技术，或分析单一的结果。迄今为止，所有关于文本摘要系统的评估工作都是由多个系统的开发人员进行的，通常是为了研究和改进句子选择技术。在TIPSTER III下，DARPA赞助了一项基于任务的多个文本摘要系统评估，这项评估的重点是用户需求，以及将摘要技术应用于各种任务的可行性。
Evaluauon is a key part of any research and development effort, but the goals and focus of evaluat:ons are often narrow m scope, addressing a specific algonthm or technique, or analyzing a single result All of the evaluation work clone to date on text summarization systems has been by the developers of mdlvldual systems, usually to study and improve sentence selection cntena Under TIPSTER III, DARPA ~s sponsoring a task-based evaluauon of multiple text summarization systems This focus of this evaluation wall be on user needs, and the feaslbdlty of applying summarization technology to a variety of tasks