Document structure
Document structure
复制标题
DOI：
10.1162/089120103322145315
复制
发表时间：
2003-06-01
影响因子：
9.3
通讯作者：
Scott, D
中科院分区：
文献类型：
--
作者：
Power, R;Bouayad-Agha, N;Scott, D
我们认为抽象文档结构是分析和生成书面文本时的一个单独的描述级别。这种表示的目的是在文本的信息（即其话语结构）和其物理表示（即其组织成图形成分，如章节、段落、句子、项目符号列表、图形和脚注）之间进行调解。抽象文档结构可以看作是Nunberg“文本语法”的延伸；它还与 HTML 和 LAT(E)X 等语言中的“逻辑”标记密切相关。我们表明，通过使用这种中间表示，可以更清晰地定义语言生成和语言理解中的几个子任务。
We argue the case for abstract document structure as a separate descriptive level in the analysis and generation of written texts. The purpose of this representation is to mediate between the message of a text (i.e., its discourse structure) and its physical presentation (i.e., its organization into graphical constituents like sections, paragraphs, sentences, bulleted lists, figures, and footnotes). Abstract document structure can be seen as an extension of Nunberg's "text-grammar"; it is also closely related to "logical" markup in languages like HTML and LAT(E)X. We show that by using this intermediate representation, several subtasks in language generation and language understanding can be defined more cleanly.