Key points are not available for this paper at this time.
νΉν μ 보κ²μμμλ κ²μ μ νλλ₯Ό λμ΄κ±°λ μ μ¬ νΉνλ€μ κ²μνκΈ° μν λͺ©μ μΌλ‘ μ²κ΅¬ν λ± νΉν κΈ°μ λ¬Έμμ λ΄μ©μ λννλ κ°μ²΄λͺ μΈμμ΄ νμνλ€. λ³Έ μ°κ΅¬μμλ νΉν κ°μ²΄λͺ μ μλμΌλ‘ μΈμνκΈ° μνμ¬ κΈ°κ³ νμ΅ κΈ°λ²μμ νκΉ λ¬Έμ ν΄κ²°μ λ§€μ° μ°μν μ±λ₯μ 보μ΄λ μ‘°κ±΄λΆ λλ€ νλ κΈ°λ²μ μ΄μ©νλ νΉν κ°μ²΄λͺ μΈμ λ°©λ²μ μ μνμλ€. κ°μ²΄λͺ νκΉ μ΄ λμ΄ μλ νΉν λ¬Έμ λ§λμΉμμ 66λ§ μ΄μ μ νμ΅μ© λ°μ΄ν°λ‘ μ¬μ©νμ¬ νΉν κ°μ²΄λͺ μμ€ν μ ꡬμΆνκ³ , 7λ§ μ΄μ μ νκ°μ© λ°μ΄ν°λ‘ μ¬μ©νμ¬ μ±λ₯ νκ°λ₯Ό νμλ€. μ€ν κ²°κ³Όμ μνλ©΄ κ°μ²΄λͺ μΈμ μ νλλ 93.6%μ΄κ³ , κ°μ²΄λͺ μΈμ μ±λ₯μ μμμ νκΉ κ²°κ³Όμ λΉκ΅νμ¬ μΌμΉλλ₯Ό νκ°νμ λ μΉ΄ν κ³μλ 0.67λ‘ λνλ¬λ€. μ΄ μΉ΄ν κ³μκ°μ λ μ¬λμ μμμ νκΉ κ²°κ³Όμ λν μΉ΄ν κ³μ 0.6 λ³΄λ€ λμ κ²μΌλ‘ νΉν κ°μ²΄λͺ μΈμ μμ€ν μ΄ μμμ νκΉ μ λμ νμ¬ μ€μ©μ μΌλ‘ νμ©λ μ μμμ νμΈνμλ€. Named entity recognition is required to improve the retrieval accuracy of patent documents or similar patents in the claims and patent descriptions. In this paper, we proposed an automatic named entity recognition for patents by using a conditional random field that is one of the best methods in machine learning research. Named entity recognition system has been constructed from the training set of tagged corpus with 660,000 words and 70,000 words are used as a test set for evaluation. The experiment shows that the accuracy is 93.6% and the Kappa coefficient is 0.67 between manual tagging and automatic tagging system. This figure is better than the Kappa coefficient 0.6 for manually tagged results and it shows that automatic named entity tagging system can be used as a practical tagging for patent documents in replacement of a manual tagging.
Lee et al. (Fri,) studied this question.