基于深度迁移学习的技术术语识别——以数控系统领域为例

被引：14

作者：

刘宇飞 ^{[1
,2
]}

尹力 ^{[3
]}

张凯 ^{[3
]}

杨建中 ^{[3
]}

郑文江 ^{[2
]}

机构：

[1] 清华大学公共管理学院

[2] 中国工程院战略咨询中心

[3] 华中科技大学机械科学与工程学院

来源：

情报杂志 | 2019年 / 38卷 / 10期

关键词：

新兴技术预见; 命名实体识别; 深度迁移学习; 数控系统; 专利分析;

D O I：

暂无

中图分类号：

TG659 [程序控制机床、数控机床及其加工]; G254 [文献标引与编目];

学科分类号：

080202 ;

摘要：

[目的/意义]新兴术语识别是新兴技术预见的一项重要工作,专利文献是技术情报的最新来源,被广泛地用于新兴技术预见。专利文献易于使用,但是术语难以挖掘、抽取难度大,存在缺乏术语标签的问题,目前未发现针对专利文献运用命名实体识别(NER)抽取技术术语的研究。[方法/过程]该文引入深度迁移学习的思想,利用成熟的公共领域源数据,运用Bi-LSTM(双向长短时记忆)模型实现跨领域迁移,有效识别技术术语并过滤高频非术语词串,通过聚类对识别术语划分技术类别。[结果/结论]以数控系统(CNC)领域专利文献为例,模型有效地将公共领域源数据已有知识迁移到科学领域目标数据,解决了专利文献少标注的问题,识别术语领域相关性强。以此划分的技术类别能为领域技术发展趋势研究提供数据支持。

引用

页码：168 / 175

页数：8

共 34 条

[1] An approach to discovering new technology opportunities: Keyword-based patent map approach[J] . Sungjoo Lee,Byungun Yoon,Yongtae Park. &nbspTechnovation . 2008 (6)
[2] Evaluating the risk of patent infringement by means of semantic patent analysis: the case of DNA chips[J] . IsumoBergmann,DanielButzke,LotharWalter,Jens P.Fuerste,Martin G.Moehrle,Volker A.Erdmann. &nbspR&D Management . 2008 (5)
[3] Using patent data for technology forecasting: China RFID patent analysis[J] . Charles V. Trappey,Hsin-Ying Wu,Fataneh Taghaboni-Dutta,Amy J.C. Trappey. &nbspAdvanced Engineering Informatics . 2010 (1)
[4] Patent-based QFD framework development for identification of emerging technologies and related business models: A case of robot technology in Korea[J] . Yonghan Ju,So Young Sohn. &nbspTechnological Forecasting & Social Change . 2014
[5] Topic based classification and pattern identification in patents[J] . Subhashini Venugopalan,Varun Rai. &nbspTechnological Forecasting & Social Change . 2014
[6] Identifying technological topics and institution-topic distribution probability for patent competitive intelligence analysis: a case study in LTE technology[J] . Bo Wang,Shengbo Liu,Kun Ding,Zeyuan Liu,Jing Xu. &nbspScientometrics . 2014 (1)
[7] Technology foresight and industrial strategy[J] . Carlo Pietrobelli,Fernanda Puppato. &nbspTechnological Forecasting & Social Change . 2015
[8] SAO network analysis of patents for technology trends identification: a case study of polymer electrolyte membrane technology in proton exchange membrane fuel cells. Sungchul Choi,Janghyeok Yoon,Kwangsoo Kim,Jae Yeol Lee,Cheol-Han Kim. Scientometrics . 2011
[9] Invention property-function network analysis of patents: a case of silicon-based thin film solar cells. Janghyeok Yoon,Sungchul Choi,Kwangsoo Kim. Scientometrics . 2011
[10] Bidirectional LSTM-CRF models for sequence tagging. HUANG Z,XU W,YU K. Computer Science . 2015

← 1 2 3 4 →