3 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 3 / 3
Yayın Sense distinction using computational methods in Turkish dictionaries(Işık Üniversitesi, 2018-01-25) Ertopçu, Burak; Solak, Ercan; Işık Üniversitesi, Fen Bilimleri Enstitüsü, Bilgisayar Mühendisliği Yüksek Lisans ProgramıNLP(Natural Language Processing) refers to general name of the study elds related with processing languages by using computer-based systems. In NLP studies, dictionaries are required as lexical and semantic resources. Because in some cases, there are necessities to match the words with their correct senses for all possible words. There are some electronic dictionaries for Turkish such as \Contemporary Turkish Dictionary(CTD)" and \Kubbealt Turkish Dictionary". However, both of these two dictionaries cover similar and redundant senses for several words. There are 86.382 words exist in CTD that written by Turkish Linguistic Society( TDK). There can be more than ten senses for a single word in some cases. By that reason, it can be hard to determine which meanings are explanatory and/or required and which of them are multiplexed needlessly. This problem of finding distinguishing senses of the words is called as \Sense Distinction Problem". The aim of this study is to simplify the sense distinction decisions by using some computational methods. In this study, we focused on to analyse the similarities of word senses by using some computational methods such as; Edit Distance, Cosine Similarity and Jaccard Index Similarity on two well-known Turkish Dictionaries Contemporary Turkish Dictionary (CTD) and Kubbealt Dictionary (KD).Yayın Rule-based chunking of semantic roles for Turkish(Işık Üniversitesi, 2018-01-24) Erkoç, Barış Can; Solak, Ercan; Işık Üniversitesi, Fen Bilimleri Enstitüsü, Bilgisayar Mühendisliği Yüksek Lisans ProgramıIn our work, we approached to semantic role labeling from a different angle. Contrary to related works, which focused on determining single role like noun phrase or predicate, we worked on all of the roles. We claim that, morphological analysis of a word and its context can be useful for semantic role labeling task. For that, we first determine the possible semantic chunk boundaries by examining the morphological analysis of words and their contexts. For further improvement in determining the boundaries, we do the first process with the combination of the morphological analysis and the boundary output from the first pass. We use these boundaries to create semantic chunks and labeled them according to their content.Yayın Morphological analyser for Turkish(Işık Üniversitesi, 2018-01-25) Özenç, Berke; Solak, Ercan; Işık Üniversitesi, Fen Bilimleri Enstitüsü, Bilgisayar Mühendisliği Yüksek Lisans ProgramıNatural Language Processing is one one the fields of work in computer science and specializes in text summarization, machine translation and many various topics. Morphology is one of the Natural Language Processing features which analyses the words with its suxes. A words meaning can change according to the sux that it takes. Turkish is an agglutinative language with rich morphological structure and set of suxes. This features of Turkish result in complex morphology structure. In this study, we present an analyser for Modern Anatolian Turkish which has high coverage on suffixes and morphological rules of Turkish. Two-Level transformation method which is convenient to design morphology of a language, consists our base of approach. We used HFST which is a Finite State Transducer implementation, as our implementation technique. The analyser covers all morphological and phonetic rules that exist in Turkish and contains a lexicon which consist of today's Turkish words. The analyser is publicly available and can be used on http://ddil.isikun.edu.tr/mortur.
