2021/01/31 by M. Standke, Abdullah Kiwan, Standke, Mark +5
Biochemistry, Genetics and Molecular Biology · Business, Management and Accounting · #68T50 #Biomedical Text Mining and Ontologies #Computation and Language (cs.CL) #E.1 #FOS: Computer and information sciences #Intellectual Property and Patents
paper · pdf · doi:10.48550/arxiv.2102.00425
openalex publication_date 2021/01/31 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
Diversity in patent language is growing and makes finding synonyms for\nconducting patent searches more and more challenging. In addition to that, most\napproaches for dealing with diverse patent language are based on manual search\nand human intuition. In this paper, a word embedding approach using statistical\nanalysis of human labeled data to produce accurate and language independent\nword vectors for technical terms is introduced. This paper focuses on the\nexplanation of the idea behind the statistical analysis and shows first\nqualitative results. The resulting algorithm is a development of the former\nEQMania UG (eqmania.com) and can be tested under eqalice.com until April 2021.\n