|
|||||
|
|
| 融合全局和局部信息的汉语宏观篇章结构识别 | |
| 引用本文： | 范亚鑫,蒋峰,朱巧明,褚晓敏,李培峰. 融合全局和局部信息的汉语宏观篇章结构识别[J]. 中文信息学报, 2022, 36(3): 1-9 |
| 作者姓名： | 范亚鑫 蒋峰 朱巧明 褚晓敏 李培峰 |
| 作者单位： | 1.苏州大学 计算机科学与技术学院,江苏 苏州 215006; 2.苏州大学 人工智能研究院,江苏 苏州 215006 |
| 基金项目： | 国家自然科学基金(61772354, 61836007, 61773276) |
| 摘 要： | 作为宏观篇章分析中的基础任务,篇章结构识别的目的是识别相邻篇章单元之间的结构,并层次化构建篇章结构树.已有的工作只考虑局部的结构和语义信息或只考虑全局信息.该文提出了一种融合全局和局部信息的指针网络模型,该模型在考虑全局语义信息的同时,又考虑局部段落间的语义关系密切程度,从而有效提高宏观篇章结构识别的能力.在汉语宏观篇... |
| 关 键 词： | 宏观篇章分析 结构识别 自顶向下 指针网络 |
Identification of Chinese Macro Discourse Structure with Global and Local Information |
|
| FAN Yaxin,JIANG Feng,ZHU Qiaoming,CHU Xiaomin,LI Peifeng. Identification of Chinese Macro Discourse Structure with Global and Local Information[J]. Journal of Chinese Information Processing, 2022, 36(3): 1-9 | |
| Authors: | FAN Yaxin JIANG Feng ZHU Qiaoming CHU Xiaomin LI Peifeng |
| Affiliation: | 1.School of Computer Science and Technology, Soochow University, Suzhou, Jiangsu 215006, China; 2.AI Research Institute, Soochow University, Suzhou, Jiangsu 215006, China |
| Abstract: | The discourse structure recognition task aims to identify the structure between adjacent discourse units for a hierarchical discourse structure tree .This paper proposes a pointer network model that integrates global and local information. It can effectively improve the ability of macro text structure recognition by considering the global semantic information and the closeness of the semantic relationship between paragraphs. The experimental results in the Chinese macro discourse Treebank(MCDTB) show that the proposed model outperforms the state-of-the-art model. |
| Keywords: | macro discourse analysis structure recognition top-down pointer network |
| 点击此处可从《中文信息学报》浏览原始摘要信息 | |
| 点击此处可从《中文信息学报》下载全文 | |