Ultra-summarization (poster abstract): a statistical approach to generating highly condensed non-extractive summaries
Ultra-summarization (poster abstract): a statistical approach to generating highly condensed non-extractive summaries
复制标题
超摘要（海报摘要）：一种生成高度浓缩的非提取摘要的统计方法
DOI：
10.1145/312624.312748
复制
发表时间：
1999
影响因子：
6.4
通讯作者：
Vibhu Mittal
中科院分区：
文献类型：
--
作者：
M. Witbrock;Vibhu Mittal
摘要使用当前的抽取式摘要技术，不可能产生比单个句子短的连贯的文档摘要，或者产生符合特定文体约束的摘要。理想情况下，人们更愿意理解文件，并直接从理解的结果中生成适当的摘要。如果没有全面的自然语言理解系统，则必须使用近似值。本文提出了一种替代的统计模型的摘要过程中，联合应用统计模型的术语选择和术语排序过程中产生简短的连贯摘要的风格从训练语料库中学习。
Abstract Using current extractive summarization techniques, it is impossible to produce a coherent document summary shorter than a single sentence, or to produce a summary that conforms to particular stylistic constraints. Ideally, one would prefer to understand the document, and to generate an appropriate summary directly from the results of that understanding. Absent a comprehensive natural language understanding system, an approximation must be used. This paper presents an alternative statistical model of a summarization process, which jointly applies statistical models of the term selection and term ordering process to produce brief coherent summaries in a style learned from a training corpus.