An Architecture for Data-to-Text Systems
An Architecture for Data-to-Text Systems
复制标题
数据到文本系统的架构
DOI：
10.3115/1610163.1610180
复制
发表时间：
2007
期刊：
影响因子：
--
通讯作者：
Ehud Reiter
中科院分区：
文献类型：
--
作者：
Ehud Reiter
我提出了一个数据到文本系统的架构，即NLG系统，它从非语言输入数据产生文本；这实际上是将Reiter和Dale（2000）的架构扩展到输入原始数据而不是人工智能知识库的系统。这个架构正在BabyTalk项目中使用，它是基于Aberdeen几个项目的经验；它似乎也与其他地方开发的许多数据到文本的系统兼容。它由四个阶段组成：信号分析，数据解释，文档规划以及微规划和实现。
I present an architecture for data-to-text systems, that is NLG systems which produce texts from non-linguistic input data; this essentially extends the architecture of Reiter and Dale (2000) to systems whose input is raw data instead of AI knowledge bases. This architecture is being used in the BabyTalk project, and is based on experiences in several projects at Aberdeen; it also seems to be compatible with many data-to-text systems developed elsewhere. It consists of four stages which are organised in a pipeline: Signal Analysis, Data Interpretation, Document Planning, and Microplanning and Realisation.