IESRL: An information extraction system for research level
LENG Fuhai; BAI Rujiang; ZHU Qingsong; Bai Rujiang (E-mail: bairj@mail.las.ac.cn)
2013-12-25
Source PublicationChinese Journal of Library and Information Science
ISSN1674-3393
Volume6Issue:4Pages:16-27
Other Abstract
Purpose: In order to annotate the semantic information and extract the research level information of research papers, we attempt to seek a method to develop an information extraction system.

Design/methodology/approach: Semantic dictionary and conditional random field model (CRFM) were used to annotate the semantic information of research papers. Based on the annotation results, the research level information was extracted through regular expression. All the functions were implemented on Sybase platform.

Findings: According to the result of our experiment in carbon nanotube research, the precision and recall rates reached 65.13% and 57.75%, respectively after the semantic properties of word class have been labeled, and F-measure increased dramatically from less than 50% to 60.18% while added with semantic features. Our experiment also showed that the information extraction system for research level (IESRL) can extract performance indicators from research papers rapidly and effectively.

Research limitations: Some text information, such as that of format and chart, might have been lost due to the extraction processing of text format from PDF to TXT files. Semantic labeling on sentences could be insufficient due to the rich meaning of lexicons in the semantic dictionary.

Research implications: The established system can help researchers rapidly compare the level of different research papers and find out their implicit innovation values. It could also be used as an auxiliary tool for analyzing research levels of various research institutions.

Originality/value: In this work, we have successfully established an information extraction system for research papers by a revised semantic annotation method based on CRFM and the semantic dictionary. Our system can analyze the information extraction problem from two levels, i.e. from the sentence level and noun (phrase) level of research papers. Compared with the extraction method based on knowledge engineering and that on machine learning, our system shows advantages of the both.
;
Purpose: In order to annotate the semantic information and extract the research level information of research papers, we attempt to seek a method to develop an information extraction system.

Design/methodology/approach: Semantic dictionary and conditional random field model (CRFM) were used to annotate the semantic information of research papers. Based on the annotation results, the research level information was extracted through regular expression. All the functions were implemented on Sybase platform.

Findings: According to the result of our experiment in carbon nanotube research, the precision and recall rates reached 65.13% and 57.75%, respectively after the semantic properties of word class have been labeled, and F-measure increased dramatically from less than 50% to 60.18% while added with semantic features. Our experiment also showed that the information extraction system for research level (IESRL) can extract performance indicators from research papers rapidly and effectively.

Research limitations: Some text information, such as that of format and chart, might have been lost due to the extraction processing of text format from PDF to TXT files. Semantic labeling on sentences could be insufficient due to the rich meaning of lexicons in the semantic dictionary.

Research implications: The established system can help researchers rapidly compare the level of different research papers and find out their implicit innovation values. It could also be used as an auxiliary tool for analyzing research levels of various research institutions.

Originality/value: In this work, we have successfully established an information extraction system for research papers by a revised semantic annotation method based on CRFM and the semantic dictionary. Our system can analyze the information extraction problem from two levels, i.e. from the sentence level and noun (phrase) level of research papers. Compared with the extraction method based on knowledge engineering and that on machine learning, our system shows advantages of the both.
KeywordResearch Papers Information Extraction Semantic Labeling Regular Expression Conditional Random Fields Research Level
Subject Area编辑出版
URL查看原文
Funding OrganizationThis work is supported by the National Social Science Foundation of China (Grant No.12CTQ032).
Document Type期刊论文
Identifierhttp://ir.las.ac.cn/handle/12502/6703
CollectionJournal of Data and Information Science_Chinese Journal of Library and Information Science-2013
Corresponding AuthorBai Rujiang (E-mail: bairj@mail.las.ac.cn)
Recommended Citation
GB/T 7714
LENG Fuhai,BAI Rujiang,ZHU Qingsong,等. IESRL: An information extraction system for research level[J]. Chinese Journal of Library and Information Science,2013,6(4):16-27.
APA LENG Fuhai,BAI Rujiang,ZHU Qingsong,&Bai Rujiang .(2013).IESRL: An information extraction system for research level.Chinese Journal of Library and Information Science,6(4),16-27.
MLA LENG Fuhai,et al."IESRL: An information extraction system for research level".Chinese Journal of Library and Information Science 6.4(2013):16-27.
Files in This Item: Download All
File Name/Size DocType Version Access License
Fuhai LENG.pdf(4090KB) 开放获取View Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[LENG Fuhai]'s Articles
[BAI Rujiang]'s Articles
[ZHU Qingsong]'s Articles
Baidu academic
Similar articles in Baidu academic
[LENG Fuhai]'s Articles
[BAI Rujiang]'s Articles
[ZHU Qingsong]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[LENG Fuhai]'s Articles
[BAI Rujiang]'s Articles
[ZHU Qingsong]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Fuhai LENG.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.