Problems Caused by Semantic Drift in WordNet Synset Construction
| Autor: | Ozlem Ergelen, Özge Bakay, Olcay Taner Yildiz |
|---|---|
| Přispěvatelé: | Işık Üniversitesi, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü, Işık University, Faculty of Engineering, Department of Computer Engineering, Yıldız, Olcay Taner |
| Rok vydání: | 2019 |
| Předmět: |
Kenet
Computer science Turkish Matchings Verbal markings WordNet Morphological markings WordNet synset construction Ontology (information science) Semantics computer.software_genre Lexical item Semantic drift Semantic change Semantic drifts Thesaurus (information retrieval) Ontology business.industry Natural language processing Wordnet Semantic drift problem False part of speech matchings Text analysis Lexical items Dictionary definitions Part of speech Natural language processing systems Turkish WordNet language.human_language POS Turkish wordnet Word sense Turkishs Dictionaries Divided synsets language Artificial intelligence Semantically-related lexical items business computer Mis-merging Separate synsets Speech matchings |
| Zdroj: | 2019 4th International Conference on Computer Science and Engineering (UBMK). |
| Popis: | In this study, we summarize the semantic drift problem that occur in specific synsets of KeNet, a Turkish WordNet, which is caused by mis-merging of semantically-related lexical items, morphological markings and false part of speech (POS) matchings. We present our approach to these problems in order to eliminate the semantic drift. We have re-analyzed the dictionary definitions of the items, placed those that possess different verbal markings into separate synsets, and divided synsets based on the POS of the items in them. Publisher's Version |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|