Chinese Patent Mining Based on Sememe Statistics and Key-Phrase Extraction

Authors:
Bo Jin;Hong-Fei Teng;Yan-Jun Shi;Fu-Zheng Qu
Affiliations:
Department of Computer Science, Dalian Univ. of Tech., P.R. China;School of Mechanical Engineering, Dalian Univ. of Tech., P.R. China;School of Mechanical Engineering, Dalian Univ. of Tech., P.R. China;School of Mechanical Engineering, Dalian Univ. of Tech., P.R. China and Key Laboratory for Precision and Non-traditional Machining Technology, Dalian Univ. of Tech., P.R. China
Venue:
ADMA '07 Proceedings of the 3rd international conference on Advanced Data Mining and Applications
Year:
2007

Citing 5
Cited 1

Generating and evaluating domain-oriented multi-word terms from texts

Information Processing and Management: an International Journal
Internet browsing and searching: user evaluations of category map and concept space techniques

Journal of the American Society for Information Science - Special topic issue: artificial intelligence techniques for emerging information systems applications
Machine Learning for Information Extraction in Informal Domains

Machine Learning - Special issue on information retrieval
Guest Editors' Introduction: Digital Libraries-Technological Advances and Social Impacts

Computer
Automatic keyphrase extraction from chinese news documents

FSKD'05 Proceedings of the Second international conference on Fuzzy Systems and Knowledge Discovery - Volume Part II

Extracting Advantage Phrases That Hint at a New Technology's Potentials

PAKM '08 Proceedings of the 7th International Conference on Practical Aspects of Knowledge Management

Quantified Score

Hi-index	0.00

Visualization

Abstract

Recently, key-phrase extraction from patent document has received considerable attention. However, the current statistical approaches of Chinese key-phrase extraction did not realize the semantic comprehension, thereby resulting in inaccurate and partial extraction. In this study, a Chinese patent mining approach based on sememe statistics and key-phrase extraction has been proposed to extract key-phrases from patent document. The key-phrase extraction algorithm is based on semantic knowledge structure of HowNet, and statistical approach is adopted to calculate the chosen value of the phrase in the patent document. With an experimental data set, the results showed that the proposed algorithm had improvements in recall from 62% to 73% and in precision from 72% to 81% compared with term frequency statistics algorithm.