SOFT COMPUTING TECHNIQUES FOR DUPLICATE QUESTION DETECTION IN TRANSLITERATED BI-LINGUAL DATA

Abstract

Instant information facilitated by Online Question & Answering (Q&A) platforms have a fundamental issue related to response time being higher and compromised answer quality. Filtering mechanism also gets corrupted by duplicate content. Another dimension to this issue relates to duplicate question detection due to transliteration used by users who are more comfortable using their native language.