A Cascaded Approach for Social Media Text Normalization of Turkish

Text normalization is an indispensable stage for natural language processing of social media data with available NLP tools. We divide the normalization prob-lem into 7 categories, namely; letter case transformation, replacement rules & lexi-con lookup, proper noun detection, deasci-ification, vowel restoration, accent nor-malization and spelling correction. We propose a cascaded approach where each ill formed word passes from these 7 mod-ules and is investigated for possible trans-formations. This paper presents the first results for the normalization of Turkish and tries to shed light on the different chal-lenges in this area. We report a 40 per-centage points improvement over a lexicon lookup baseline and nearly 50 percentage points over available spelling correctors.