收录:
摘要:
Information extraction is the fundamental technique for text-based patent analysis in era of big data. However, the specialty of patent text enables the performance of general information-extraction methods to reduce noticeably. To solve this problem, an in-depth exploration has to be done for clarify the particularity in patent information extraction, thus to point out the direction for further research. In this paper, we discuss the particularity of patent information extraction in three aspects: (1) what is the special about labeled patent dataset? (2) What is special about word embeddings in patent information extraction? (3) What kind of method is more suitable for patent information extraction? © 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
关键词:
通讯作者信息:
电子邮件地址:
来源 :
ISSN: 1613-0073
年份: 2020
卷: 2658
页码: 63-72
语种: 英文
归属院系: