Alignment between a technical paper and presentation sheets using a hidden Markov model
Alignment between a technical paper and presentation sheets using a hidden Markov model
复制标题
DOI：
10.1109/amt.2005.1505278
复制
发表时间：
2005-05
期刊：
影响因子：
--
通讯作者：
Tessai Hayama;Hidetsugu Nanba;S. Kunifuji
中科院分区：
文献类型：
--
作者：
Tessai Hayama;Hidetsugu Nanba;S. Kunifuji
我们一直在研究从技术论文自动生成演示文稿。我们的方法包括获得一组规则，通过应用机器学习技术，许多对技术论文和他们的演示文稿从万维网上收集的演示文稿生成表。作为第一步，在本文中，我们提出了一种方法，对齐技术文件和演示文稿。我们的方法是基于Jing的方法，它使用了隐马尔可夫模型（HMM）。虽然这种方法对报纸文章中的短句对齐很有用，但它不适用于包含图表和长句的论文中的句子对齐。因此，我们分析了纸张和纸张的特征，如来自文本外观的信息，并提出了一种将这些特征和Jing方法相结合的对齐方法。评估表明，我们的对齐方法进行了有效的。
We have been studying the automatic generation of presentation sheets from a technical paper. Our approach consists of obtaining a set of rules for generating presentation sheets by applying machine learning techniques to many pairs of technical papers and their presentation sheets collected from the World Wide Web. As a first step, in this paper, we propose a method for aligning technical papers and presentation sheets. Our method is based on Jing's method, which uses a hidden Markov model (HMM). Although this method is useful to align short sentences in newspaper articles, it is inapplicable to align sentences in a paper including charts and long sentences. Therefore, we analyse features of papers and sheets, such as information from text appearance, and propose an alignment method that combines the use of these features and Jing's method. The evaluation shows that our alignment method performed effectively.