Results 1 -
6 of
6
DOCTORAL DISSERTATIONS 158/2012 Learning Constructions of Natural Language: Statistical Models and Evaluations
"... Language English Article dissertation (summary + original articles) The modern, statistical approach to natural language processing relies on using machine learning techniques on the increasing amount of text and speech data in electronic format. Typical applications for statistical methods include ..."
Abstract
- Add to MetaCart
Language English Article dissertation (summary + original articles) The modern, statistical approach to natural language processing relies on using machine learning techniques on the increasing amount of text and speech data in electronic format. Typical applications for statistical methods include information retrieval, speech recognition, and machine translation. Many problems encountered in the applications can be solved without language-dependent resources, such as annotated data sets, by the means of unsupervised learning. This thesis focuses on one such problem: the selection of lexical units. It is the first
– Real-Time Systems
, 2010
"... Copyright c ○ 2010 by the authors. Scope of the Symposium The aim of the York Doctoral Symposium (YDS) is to establish a platform for dissemination and exchange of up-to-date scientific information on theoretical, generic and applied areas of computing by giving doctoral students an opportunity for ..."
Abstract
- Add to MetaCart
(Show Context)
Copyright c ○ 2010 by the authors. Scope of the Symposium The aim of the York Doctoral Symposium (YDS) is to establish a platform for dissemination and exchange of up-to-date scientific information on theoretical, generic and applied areas of computing by giving doctoral students an opportunity for presenting their ongoing research in computer science and scientific computing. In particular, the symposium intends to bring together young researchers who are active in this wide field and interested in an interdisciplinary exchange of ideas and experience. The symposium also strives to promote research and development for the improvement of interdisciplinary applications of computing. Topics include, but are not restricted to: – Artificial Intelligence
– Database Systems – Distributed Systems
, 2010
"... Copyright c ○ 2010 by the authors. Scope of the Symposium The aim of the York Doctoral Symposium (YDS) is to establish a platform for dissemination and exchange of up-to-date scientific information on theoretical, generic and applied areas of computing by giving doctoral students an opportunity for ..."
Abstract
- Add to MetaCart
(Show Context)
Copyright c ○ 2010 by the authors. Scope of the Symposium The aim of the York Doctoral Symposium (YDS) is to establish a platform for dissemination and exchange of up-to-date scientific information on theoretical, generic and applied areas of computing by giving doctoral students an opportunity for presenting their ongoing research in computer science and scientific computing. In particular, the symposium intends to bring together young researchers who are active in this wide field and interested in an interdisciplinary exchange of ideas and experience. The symposium also strives to promote research and development for the improvement of interdisciplinary applications of computing. Topics include, but are not restricted to: – Artificial Intelligence – Bioinformatics and Mathematics
Unsupervised Morphological Analysis Using
"... Abstract. This article presents an unsupervised morphological analysis algorithm to segment words into roots and affixes. The algorithm relies on word occurrences in a given dataset. Target languages are English, Finnish, and Turkish, but the algorithm can be used to segment any word from any langua ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract. This article presents an unsupervised morphological analysis algorithm to segment words into roots and affixes. The algorithm relies on word occurrences in a given dataset. Target languages are English, Finnish, and Turkish, but the algorithm can be used to segment any word from any language given the wordlists acquired from a corpus consisting of words and word occurrences. In each iteration, the algorithm divides words with respect to occurrences and constructs a new trie for the remaining affixes. Preliminary experimental results on three languages show that our novel algorithm performs better than most of the previous algorithms.
DATE OF APPROVAL: 29/04/2011 Acknowledgements
, 2011
"... I am honored to present my special thanks and deepest gratitude to my supervisor Assist. Prof. Olcay Taner YILDIZ for his guidance in this thesis. Without his endless patience and support I would not finish this work. I am feeling lucky to share his vision and knowledge throughout this thesis. I am ..."
Abstract
- Add to MetaCart
(Show Context)
I am honored to present my special thanks and deepest gratitude to my supervisor Assist. Prof. Olcay Taner YILDIZ for his guidance in this thesis. Without his endless patience and support I would not finish this work. I am feeling lucky to share his vision and knowledge throughout this thesis. I am also grateful to my family for their support. They have always been by my side whenever I needed.
SANTA B. BASNET
, 2011
"... Unsupervised morpheme segmentation in a non-parametric ..."
(Show Context)
