Integrating Discourse Markers into a Pipelined Natural Language Generation Architecture
Integrating Discourse Markers into a Pipelined Natural Language Generation Architecture
复制标题
将话语标记集成到流水线自然语言生成架构中
DOI：
10.3115/1075096.1075130
复制
发表时间：
2003
期刊：
影响因子：
--
通讯作者：
Charles B. Callaway
中科院分区：
文献类型：
--
作者：
Charles B. Callaway
流水线自然语言生成(NLG)系统变得越来越复杂，因为添加了体系结构模块来支持语言功能，如引用表达式、词汇选择和修订。这引发了关于这些新模块在整体架构中的相对位置的讨论。最近关于多段落文本的另一个方面--话语标记语的研究表明，是时候考虑话语标记语插入算法的适用范围了。我们给出的例子表明，在流水线NLG体系结构中，最好的方法是将其强烈地绑定到修订组件。最后，我们在一个工作的多页面系统中对该方法进行了评估。
Pipelined Natural Language Generation (NLG) systems have grown increasingly complex as architectural modules were added to support language functionalities such as referring expressions, lexical choice, and revision. This has given rise to discussions about the relative placement of these new modules in the overall architecture. Recent work on another aspect of multi-paragraph text, discourse markers, indicates it is time to consider where a discourse marker insertion algorithm fits in. We present examples which suggest that in a pipelined NLG architecture, the best approach is to strongly tie it to a revision component. Finally, we evaluate the approach in a working multi-page system.