Fast and Accurate Patent Classification in Search Engines

Авторы

Ядринцев В. В. Соченков И. В.

Аннотация

This article presents a new approach to large scale patent classification. The need to classify documents often takes place in professional information retrieval systems. In this paper we describe our approach, based on linguistically-supported k-nearest neighbors. We experimentally evaluate it on the Russian and English datasets and compare modern classification technique fastText. We show that KNN is a viable alternative to traditional text classifiers, achieving comparable accuracy while using less additional hardware resources.

Внешние ссылки

DOI: http://dx.doi.org/10.1088/1742-6596/1117/1/012004

РИНЦ: https://elibrary.ru/item.asp?id=38639840

Читать на ResearchGate (на англ.): https://www.researchgate.net/publication/329216402_Fast_and_Accurate_Patent_Classification_in_Search_Engines

РУДН. Репозиторий: https://repository.rudn.ru/ru/records/article/record/36232/

Ссылка при цитировании

Yadrintsev, V., Bakarov, A., Suvorov, R., & Sochenkov, I. Fast and Accurate Patent Classification in Search Engines // Journal of Physics: Conference Series. – IOP Publishing, 2018. – Т. 1117. – №. 1. – С. 012004.