A Simple Approach to Unify Ambiguously Encoded Kurdish Characters

Jaf, Sardar

Abstract

In this study we outline a potential problem in the normalisation stage of processing texts that are based on a modified version of the Arabic alphabet. The main source of resources available for processing resource-scarce languages is raw text. We have identified an interesting challenge that must be addressed when normalising certain natural language texts. Many lessresourced languages, such as Kurdish, Farsi, Urdu, Pashtu, etc., use a modified version of the Arabic writing system. Many characters in harvested data from the Internet may have exactly the same form but encoded with different Unicode values (ambiguous characters). It is important to identify ambiguous characters during the normalisation stage of most text processing tasks. We will demonstrate cases related to ambiguous Kurdish and Farsi characters and propose a semi-automatic approach to identifying and unifying ambiguously encoded characters.

Citation

Jaf, S. (2016, September). A Simple Approach to Unify Ambiguously Encoded Kurdish Characters. Presented at Second International Conference of Computational Linguistics in Bulgaria, Sofia, Bulgaria

• Presentation Conference Type: Conference Paper (published)
• Conference Name: Second International Conference of Computational Linguistics in Bulgaria
• Start Date: Sep 9, 2016
• Acceptance Date: Jul 27, 2016
• Publication Date: Sep 9, 2016
• Deposit Date: Aug 22, 2016
• Publicly Available Date: Aug 23, 2016
• Pages: 86-94
• Series ISSN: 2367-5578,2367-5675
• Public URL: https://durham-repository.worktribe.com/output/1150394
• Publisher URL: http://dcl.bas.bg/clib/proceedings/