A Mixture Record Linkage Approach for US Patent Inventor Disambiguation.
Guan-Can YangCheng LiangZhang JingDao-Ren WangHai-Chao ZhangPublished in: MUE/FutureTech (2017)
Keyphrases
- record linkage
- privacy preserving
- data cleaning
- duplicate detection
- mixture model
- natural language processing
- approximate matching
- intellectual property
- word sense disambiguation
- multiple databases
- entity resolution
- linked data
- information retrieval
- natural language
- co occurrence
- patent documents
- gaussian distribution
- wordnet
- expectation maximization
- census data
- data mining
- prior art
- patent information
- cross language information retrieval
- disclosure risk
- patent retrieval
- information technology
- machine learning