Combining Knowledge and CRF-Based Approach to Named Entity Recognition in Russian

Abstract

Current machine-learning approaches to information extraction often include features based on large volumes of knowledge in form of gazetteers, word clusters, etc. In this paper we consider a CRF-based approach to Russian named entity recognition based on multiple lexicons. We test our system on the open Russian collection "Persons-1000" labeled with… (More)
DOI: 10.1007/978-3-319-52920-2_18

9 Figures and Tables

Topics

  • Presentations referencing similar topics