DeASCIIfication approach to handle diacritics in Turkish information retrieval

作者:

Highlights:

• Risk-sensitive evaluation of approaches for handling diacritics in Turkish information retrieval.

• Application of diacritics restoration to Turkish information retrieval.

• Investigation of the diacritics sensitivity of stemming algorithms.

摘要

•Risk-sensitive evaluation of approaches for handling diacritics in Turkish information retrieval.•Application of diacritics restoration to Turkish information retrieval.•Investigation of the diacritics sensitivity of stemming algorithms.

论文关键词:Accents,DeASCIIfier,Diacritics restoration,Risk-sensitive evaluation,Stemming,Turkish information retrieval

论文评审过程:Received 29 July 2014, Revised 21 August 2015, Accepted 28 August 2015, Available online 10 November 2015, Version of Record 19 February 2016.

论文官网地址:https://doi.org/10.1016/j.ipm.2015.08.004