Ranking Assisted Unsupervised Morphological Disambiguation of Turkish

Basit Öğe Kaydı
dc.authorid0000-0002-2680-5419
dc.contributor.authorAgun, Hayri Volkan
dc.contributor.authorAslan, Ozkan
dc.date.accessioned2026-02-08T15:15:41Z
dc.date.available2026-02-08T15:15:41Z
dc.date.issued2025
dc.departmentBursa Teknik Üniversitesi
dc.description.abstractIn comparison to English, Turkish is an agglutinative language with fewer resources. The agglutinative properties of words result in a significant number of morphological analyses, creating uncertainty in morphological disambiguation and syntactic parsing. Traditional approaches typically rely on supervised learning models based on the correct morphological analysis of a given phrase. In this study, we propose a ranking method to limit and filter out irrelevant morphological tags from all possible combinations of morphological analyses of a given sentence without supervision. The suggested method selects less ambiguous analyses for statistical aggregation and applies inference through the PageRank algorithm on a densely connected graph. Subsequently, this graph is utilized to develop a voting schema for each test word based on the connections in the test sentence. Experimental evaluations of the proposed methods on three independently and manually annotated test datasets indicate a token accuracy of approximately 80% and an accuracy of around 61% for ambiguous tokens. In all ranking evaluations, the best scores from the PageRank variations significantly outperform those of Self-Attention LSTM and ELMO deep learning models. The training process of PageRank is notably straightforward and efficient, requiring O(n(2)) parameter adjustments, which is considerably fewer than those required by the backpropagation method used in neural network training. Furthermore, to reduce ambiguity in sentences from different genres with scarce samples, the proposed method is easily adaptable.
dc.identifier.doi10.1109/ACCESS.2025.3547303
dc.identifier.endpage41983
dc.identifier.issn2169-3536
dc.identifier.scopus2-s2.0-105001061343
dc.identifier.scopusqualityQ1
dc.identifier.startpage41974
dc.identifier.urihttps://doi.org/10.1109/ACCESS.2025.3547303
dc.identifier.urihttps://hdl.handle.net/20.500.12885/5895
dc.identifier.volume13
dc.identifier.wosWOS:001446493800020
dc.identifier.wosqualityQ2
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherIeee-Inst Electrical Electronics Engineers Inc
dc.relation.ispartofIeee Access
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzWOS_KA_20260207
dc.subjectAccuracy
dc.subjectTraining
dc.subjectAnalytical models
dc.subjectLong short term memory
dc.subjectTuning
dc.subjectTraining data
dc.subjectSurface morphology
dc.subjectSupervised learning
dc.subjectNatural language processing
dc.subjectIndexes
dc.subjectMorphological disambiguation
dc.subjectdeep neural networks
dc.subjectfeature engineering
dc.subjectunsupervised learning
dc.titleRanking Assisted Unsupervised Morphological Disambiguation of Turkish
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu