1 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 1 / 1
Yayın Unsupervised morphological analysis using tries(Işık Üniversitesi, 2011-04-29) Ak, Koray; Yıldız, Olcay Taner; Işık Üniversitesi, Fen Bilimleri Enstitüsü, Bilgisayar Mühendisliği Yüksek Lisans ProgramıMorphological analysis or decomposition studies the structure, formation, function of words, identifies the morphemes (smallest meaning-bearing elements) of the language and attempts to formulate rules that model the language. It is widely used in different areas such as speech recognition, machine translation, information retrieval, text understanding, and statistical language modeling. Considering that the natural language processing applications are dealing with large amounts of data, it is not feasible to use linguists to analyze text corpus by hand, the complexity and real time Processing requirements leads to automated morphological analysis. As an alternative to the hand-made systems, there exist algorithms that work unsupervised manner and autonomously do morphological analysis for the words in an unannotated text corpus. In this thesis, an unsupervised leaming algorithm is proposed to extract infor-mation about the text corpus and the model of the language. The proposed algorithm constructs a trie that consists of characters and the occurrences of the words as nodes. The algorithm then detects roots of the given words by examining the occurrences in the path of the word. When the root is revealed, the algorithm creates a new trie from the affix parts, left after the root for each word. The algorithm continues recursively until there is no affbc left to process. Experimental results on three languages (Finnish, English and Turkish) show that our novel algorithm performs better than most of the previous algorithms in the field.
