{"paper":{"title":"Non-Standard Words as Features for Text Categorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Sanda Martin\\v{c}i\\'c-Ip\\v{s}i\\'c, Slobodan Beliga","submitted_at":"2014-08-28T15:06:50Z","abstract_excerpt":"This paper presents categorization of Croatian texts using Non-Standard Words (NSW) as features. Non-Standard Words are: numbers, dates, acronyms, abbreviations, currency, etc. NSWs in Croatian language are determined according to Croatian NSW taxonomy. For the purpose of this research, 390 text documents were collected and formed the SKIPEZ collection with 6 classes: official, literary, informative, popular, educational and scientific. Text categorization experiment was conducted on three different representations of the SKIPEZ collection: in the first representation, the frequencies of NSWs "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1408.6746","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}