基于LDA的科技创新主题语义识别研究

doi:10.13266/j.issn.0252-3116.2015.14.018

图书情报工作 ›› 2015, Vol. 59 ›› Issue (14): 126-134.DOI: 10.13266/j.issn.0252-3116.2015.14.018

基于LDA的科技创新主题语义识别研究

祝娜, 王效岳, 杨京, 白如江

山东理工大学科技信息研究所淄博 255049

收稿日期:2015-04-27 修回日期:2015-06-20 出版日期:2015-07-20 发布日期:2015-07-20
作者简介:祝娜,硕士研究生,E-mail:742725186@qq.com;王效岳,教授,硕士生导师;杨京,硕士研究生;白如江,副研究馆员,硕士生导师
基金资助:
本文系教育部人文社会科学研究青年基金"长句检索中信息查询扩展研究"(编号:12YJC870001)和文化部科技创新项目"大规模学术文献并行处理与自动分类研究"研究成果之一。

Semantic Recognition of Technological Innovation Theme Based on LDA

Zhu Na, Wang Xiaoyue, Yang Jing, Bai Rujiang

Institute of Scientific & Technical Information, Shandong University of Technology, Zibo 255049

Received:2015-04-27 Revised:2015-06-20 Online:2015-07-20 Published:2015-07-20

摘要/Abstract

摘要：

[目的/意义] 由于传统科技创新主题概率识别方法忽略文本内容语义理解,为了更加准确地识别出主题,科技创新主题语义识别势在必行。[方法/过程] 提出一种基于LDA的科技创新主题语义识别方法,利用语义角色标注技术对科技文献中的科技创新内容进行语义标引,构建LDA主题语义识别模型,根据表征科技创新内容的关键词语义角色对应的上位词的概率识别出科技创新主题。[结果/结论] 通过以3D打印领域数据为对象进行实验,证明该方法能够更加准确地识别出科技创新主题,形成科技创新主题-主题词-科技文献的混合分布聚类集群,减少研究背景等无关数据干扰,避免语义含义相同的科技创新主题词重复统计问题。

关键词: 语义角色标注, 科技创新主题, LDA模型, 3D打印

Abstract:

[Purpose/significance] Traditional probabilistic model of technology innovation theme identification method ignores the semantic understanding of the text. In order to identify the theme more accurately, the semantic recognition of technological innovation theme is imperative.[Method/process] This article proposes a semantic recognition method of science and technology innovation theme based LDA, uses the semantic role labeling technique to semantic index the technological innovation content of scientific literature, builds the LDA topic semantic recognition model, and identifies the science and technology innovation theme according to the probability of the hypernyms which correspond with semantic roles of keywords from technological innovation content.[Result/conclusion] The 3D printing field data experimental results show that, this method can identify the innovation theme more accurately, and form a mixed distribution cluster of scientific and technological innovation theme-scientific and technological innovation MeSH-scientific literature. It can reduce the interference of the background and other irrelevant data and avoid of the same semantic meaning's double counting problem of scientific and technological innovation MeSH.

Key words: semantic role labeling, technological innovation theme, LDA model, 3D printing

中图分类号:

G250.2

祝娜, 王效岳, 杨京, 白如江. 基于LDA的科技创新主题语义识别研究[J]. 图书情报工作, 2015, 59(14): 126-134.

Zhu Na, Wang Xiaoyue, Yang Jing, Bai Rujiang. Semantic Recognition of Technological Innovation Theme Based on LDA[J]. LIS, 2015, 59(14): 126-134.

参考文献

[1] Matsumura N, Matsuo Y, Ohsawa Y, et al. Discovering emerging topics from WWW[J]. Journal of Contingencies and Crisis Management, 2002, 10(2):73-81.
[2] 崔凯,周斌,贾焰,等. 一种基于LDA的在线主题演化挖掘模型[J]. 计算机科学,2010(11):156-159,193.
[3] 叶春蕾,冷伏海. 基于引文——主题概率模型的科技文献主题识别方法研究[J]. 情报理论与实践,2013(9):100-103.
[4] 王平. 基于层次概率主题模型的科技文献主题发现及演化[J]. 图书情报工作,2014,58(22):70-77.
[5] 邹杰利. 基于条件随机场的中文图书主题自动标引研究[D].南京:南京大学,2013.
[6] 孟令恩,李颖,何彦青,等. 基于语义角色标注的专利主题提取研究[J]. 图书情报工作,2014,58(19):19-24.
[7] Nallapati R, Mcfarland D A, Manning C D. Topic flow model:Unsupervised learning of topic-specific influences of hyperlinked documents[J].Journal of Machine Learning Research-Proceedings Track, 2011,15(1):543-551.
[8] [EB/OL]. [2015-01-10].http://blog.sina.com.cn/s/blog_4caedc7a0102eq8m.html.
[9] Havre S, Hetzler E, Whitney P, et al. ThemeRiver:Visualizing thematic changes in large document collections[J]. IEEE Transactions on Visualization and Computer Graphics, 2002, 8(1):9-20.
[10] Chi Huai-Hsin. Improving Web usability through visualization[J]. Internet Computing, 2002, 6(2):64-71.
[11] [EB/OL]. [2015-01-10].http://www.worldwidetelescope.org/.
[12] [EB/OL]. [2015-01-10].http://www.wolframalpha.com/.
[13] 杨选选,张蕾. 基于语义角色和概念图的信息抽取模型[J]. 计算机应用,2010(2):411-414.
[14] Beeferman D, Berger A, Lafferty J. Statistical models for text segmentation[J]. Machine Learning, 1999, 34(1-3):177-210.
[15] 汪红林,王红玲,周国栋. 基于依存关系的语义角色标注[J]. 计算机工程,2009(15):82-84.
[16] 李纲,戴强斌. 基于词汇链的关键词自动标引方法[J]. 图书情报知识,2011(3):67-71.
[17] Fabra J, Hernández S,Álvarez P, et al. A practical experience concerning the parallel semantic annotation of a large-scale data collection[C]//Proceedings of the 9th International Conference on Semantic Systems. New York:ACM, 2013:65-72.
[18] Alves da Silva M A, Teixeira Belloze K, Cavalcanti M C, et al. Agile semantic annotation of scientific texts at the biomedical scenario[C]//e-Science (e-Science), 2014 IEEE 10th International Conference on. Sao Paulo:IEEE, 2014:100-107.
[19] 张泽宇,李莉,谭凤,等. 基于语义的文档标注方法研究[J]. 计算机工程与科学,2013(9):151-156.
[20] 熊皓,刘群,吕雅娟. 联合语义角色标注和指代消解[J]. 中文信息学报,2013(6):58-68.
[21] 白如江,王晓笛,王效岳. 基于支持向量机和核心特征词的科技文献自动标引研究[J]. 情报理论与实践,2014(7):129-134.
[22] Tamilin A, Magnini B, Serani L. Context-driven semantic enrichment of Italian news archive[C]//Proceedings of the 7th International Conference on the Semantic Web:Research and Applications. Heraklion:Springer, 2010:364-378.
[23] Ciancarini P, Di Iorio A, Nuzzolese A G, et al. Semantic annotation of scholarly documents and citations[M]//AI* IA 2013:Advances in Artificial Intelligence. Turin:Springer, 2013:336-347.
[24] Blei D M, Ng A Y, Jordan M I. Latent Dirichlet allocation[J]. The Journal of Machine Learning Research, 2003(3):993-1022.
[25] 李保利,杨星. 基于LDA模型和话题过滤的研究主题演化分析[J]. 小型微型计算机系统,2012,33(12):2738-2743.
[26] Riedl M, Biemann C. TopicTiling:A text segmentation algorithm based on LDA[C]//Proceedings of ACL 2012 Student Research Workshop. Pennsylvania:ACM,2012:37-42.
[27] 胡吉明,陈果. 基于动态 LDA 主题模型的内容主题挖掘与演化[J]. 图书情报工作, 2014, 58(2):138-142.
[28] Guo Yufan, Silins I, Reichart R, et al. CRAB Reader:A tool for analysis and visualization of argumentative zones in scientific literature[C]//COLING 2012, 24th International Conference on Computational Linguistics. Mumbai:Indian Institute of Technology Bombay, 2012. 183-190.
[29] Hirohata K, Okazaki N, Ananiadou S, et al. Identifying sections in scientific abstracts using conditional random fields[C]//Proceedings of The 3rd International Joint Conference on Natural Ianguage Processing.Hyderabad:Asian Federation of Natural Language Processing,2008. 381-388.
[30] Basili R, Moschitti A, Pazienza M T. A text classifier based on linguistic processing[OL].[2015-04-20].http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.39.5608&rep=rep1&type=pdf.
[31] Ohsawa Y, Benson N E, Yachida M. KeyGraph:Automatic indexing by co-occurrence graph based on building construction metaphor[C]//Research and Technology Advances in Digital Libraries, 1998.Santa Barbara:IEEE, 1998:12-18.
[32] Galligan M C, Saldova R, Campbell M P, et al. Greedy feature selection for glycan chromatography data with the generalized Dirichlet distribution[J]. BMC Bioinformatics,2013,14(1):1-25.
[33] 吴平. 3D打印技术及其未来发展趋势[J]. 印刷质量与标准化,2014(1):8-10.
[34] Miller G A. WordNet:A Lexical Database for English[J]. Communications of the ACM,1995, 38(11):39-41.
[35] Graetz N. Teaching EFL students to extract structural information from abstracts:Reading for Professional Purposes:Methods and Materials in Teaching Languages[C]//The International Symposium on Language for Special Purposes.Eindhoven:ERIC,1982.
[36] Chang Chih-Chung, Lin Chih-Jen. LIBSVM:A library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology (TIST), 2011, 2(3):389-396.

基于LDA的科技创新主题语义识别研究

Semantic Recognition of Technological Innovation Theme Based on LDA

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	李倩, 王帅. LDA模型下我国公共图书馆微信平台阅读推广内容主题研究[J]. 图书情报工作, 2022, 66(8): 72-83.
[2]	吕鲲, 陈箫羽, 靖继鹏. 基于组合分词方法和LDA模型的区块链金融产业关键技术识别研究[J]. 图书情报工作, 2022, 66(19): 110-121.
[3]	王秀红, 高敏. 基于BERT-LDA的关键技术识别方法及其实证研究——以农业机器人为例[J]. 图书情报工作, 2021, 65(22): 114-125.
[4]	王康, 高继平, 潘云涛, 陈悦. 多位态研究主题识别及其演化路径方法研究[J]. 图书情报工作, 2021, 65(11): 113-122.
[5]	蒋甜, 刘小平, 刘会洲. 基于关键词关联度指标(KRI)进行LDA噪声主题过滤的方法研究[J]. 图书情报工作, 2020, 64(3): 92-99.
[6]	张泰瑞, 陈渝. 基于LDA模型因素提取的健康信息用户转移行为研究[J]. 图书情报工作, 2019, 63(21): 66-77.
[7]	秦玥, 吴亚平, 王继民. 中国政府网“一带一路”新闻话题挖掘分析[J]. 图书情报工作, 2019, 63(15): 103-110.
[8]	李秀霞, 宋凯. STCF值:基于研究主题的学术文献影响力评价新指标[J]. 图书情报工作, 2018, 62(20): 88-94.
[9]	杨超, 朱东华, 汪雪锋, 朱福进, 衡晓帆. 专利技术主题分析:基于SAO结构的LDA主题模型方法[J]. 图书情报工作, 2017, 61(3): 86-96.
[10]	杨春艳, 潘有能, 赵莉. 基于语义和引用加权的文献主题提取研究[J]. 图书情报工作, 2016, 60(9): 131-138,146.
[11]	孟令恩, 李颖, 何彦青, 屈鹏, 王惠临. 基于语义角色标注的专利主题提取研究[J]. 图书情报工作, 2014, 58(19): 19-24.
[12]	王晓笛, 祝娜, 白如江, 王效岳. 基于语义角色标注的文献相似度检测研究[J]. 图书情报工作, 2014, 58(12): 130-135.
[13]	张世佳, 曲建升. 图书馆引入3D打印服务的意义与前景[J]. 图书情报工作, 2014, 58(05): 41-47.
[14]	胡吉明, 陈果. 基于动态LDA主题模型的内容主题挖掘与演化[J]. 图书情报工作, 2014, 58(02): 138-142.
[15]	唐晓波, 王洪艳. 基于潜在语义分析的微博主题挖掘模型研究[J]. 图书情报工作, 2012, 56(24): 114-119.