|
|
|
| Semantic Recognition and Classification Method of Innovation Points in Scientific and Technological Abstracts |
| Wen Hao |
| School of Information and Control Engineering, Xi an University of Architecture Technology, Xi an 710055 |
|
|
|
|
Abstract The published scientific and technical abstracts provide reliable semantic fact data of problems, methods, and results in scientific research activities, and lay a solid foundation for the dissemination of innovative points and the discovery of new interdisciplinary knowledge. Their accurate identification and separation will be a key issue in the use of artificial intelligence technology to realize an innovative factual knowledge question and answer system. This paper proposes an innovative point semantic recognition and classification method. On this method, scientific and technological abstracts are firstly classified as 6 kinds according to their syntactic and semantic functions. Secondly, the results of the classification are analyzed with statistical analysis of the number distribution of classes and sentence positions, sentence types and the structural features of sentence semantic positions, and the semantic word order characteristics of abstract sentences are tested. Finally, the second classification and merging are carried out which is based on the previous analysis, so and the classification of the innovation points, methods and results of scientific and technological abstracts is realized. The accuracy rate of classification is 99%. The experimental results show that this method has the advantages of simple algorithm, high classification accuracy, and good universality.
|
|
Received: 13 August 2018
|
|
|
|
1 引文索引[EB/OL]. [2018-6-3]. https://baike.baidu.com/item/%E5%BC%95%E6%96%87%E7%B4%A2%E5%BC%95/8017877?fr=aladdin.
2 ChangS J, RiceR E. Browsing: A multidimensional framework[J]. Annual Review of Information Science and Technology, 1993, 28(4): 231-276.
3 CanoV. Citation behavior: classification, utility, and location[J]. Journal of the American Society for Information Science, 1989, 40(4): 284-290.
4 袁慧, 马建霞, 王文娟. 期刊引用行为与影响因子的关系[J]. 中国科技期刊研究, 2017, 28(11): 1058-1064.
5 陆伟, 孟睿, 刘兴帮. 面向引用关系的引文内容标注框架研究[J]. 中国图书馆学报, 2014, 40(6): 93-104.
6 郭全中. 创新知识服务——推动出版业转型发展[J]. 出版广角, 2018, 3(9): 29-31.
7 江锦年. 出版业知识服务创新的发展策略[J]. 新闻与写作, 2017(10): 101-103.
8 张晓林. 走向知识服务——寻找新世纪图书情报工作的生长点[J]. 中国图书馆学报, 2000, 11(5): 32-37.
9 刘寅斌, 胡亚萍. 从谷歌大脑看人工智能在知识服务上的应用[J]. 图书与情报, 2017, 20(6): 112-116.
10 化柏林. 学术论文中方法知识元的类型与描述规则研究[J]. 中国图书馆学报, 2016, 42(1): 30-40.
11 温浩, 乔晓东. 文摘创新点的语义本体模型研究[J]. 情报学报, 2017, 36(9): 964-971. |
|
|
|
