| 基于深度学习的学术文本段落结构功能识别研究 |
| |
| 引用本文： | 王倩,曾金,刘家伟,戚越.基于深度学习的学术文本段落结构功能识别研究[J].情报科学,2020,38(3):64-69. |
| |
| 作者姓名： | 王倩 曾金 刘家伟 戚越 |
| |
| 作者单位： | 武汉大学信息管理学院;武汉大学信息检索与知识挖掘研究所;湖北经济学院信息管理与统计学院 |
| |
| 基金项目： | 国家自然科学基金面上项目“基于多语义信息融合的学术文献引文推荐研究”(71673211). |
| |
| 摘 要： | 【目的/意义】在学术大数据的应用背景下,对学术文本更加细粒度、语义化的分析挖掘日益迫切,学术文本结构功能识别成为科研领域的一个研究热点。【方法/过程】本文从段落的层次来识别章节结构功能,提出利用结合卷积神经网络和循环神经网络的特征对学术文本段落进行表达,然后进行分类。【结果/结论】文本提出的深度学习方法在整体分类结果上优于传统的机器学习方法,同时极大的减少了传统特征工程的人力需求。
|
| 关 键 词： | 结构功能 深度学习 文本分类 学术文本 特征提取 |
Structure Function Recognition of Academic Text Paragraph Based on Deep Learning |
| |
| WANG Qian,ZENG Jin,LIU Jia-wei,QI Yue.Structure Function Recognition of Academic Text Paragraph Based on Deep Learning[J].Information Science,2020,38(3):64-69. |
| |
| Authors: | WANG Qian ZENG Jin LIU Jia-wei QI Yue |
| |
| Institution: | (School of Information Management,Wuhan University,Wuhan 430072,China;Institute for Information Retrieval and Knowledge Mining,Wuhan University,Wuhan 430072,China;School of Information Management and Statistics,Hubei University of Economics,Wuhan 430205,China) |
| |
| Abstract: | 【Purpose/significance】In the application background of academic big data, more granular and semantic analysis of academic texts is becoming increasingly urgent. Thus, the structure function recognition of academic texts has become a hot research topic.【Method/process】This paper recognizes section function on paragraph level, proposes to use the characteristics of convolutional neural network and recurrent neural network to express the text of academic texts and then classify them.【Results/conclusion】The deep learning method proposed in this paper is superior to the traditional machine learning method in the overall classification results, but also greatly reduces the manpower requirements of traditional feature engineering. |
| |
| Keywords: | structure function deep learning text classification academic text feature extraction |
| 本文献已被 维普 等数据库收录！ |
| 点击此处可从《情报科学》浏览原始摘要信息 |
| 点击此处可从《情报科学》下载免费的PDF全文 |
|
