Loading...
Search for:
discriminative-models
0.006 seconds
Discriminative spoken language understanding using statistical machine translation alignment models
, Article Communications in Computer and Information Science ; Vol. 427, issue , Sep , 2014 , pp. 194-202 ; ISSN: 18650929 ; ISBN: 9783319108490 ; Khadivi, S ; Ghidary, S. S ; Bokaei, M. H ; Sharif University of Technology
Abstract
In this paper, we study the discriminative modeling of Spoken Language Understanding (SLU) using Conditional Random Fields (CRF) and Statistical Machine Translation (SMT) alignment models. Previous discriminative approaches to SLU have been dependent on n-gram features. Other previous works have used SMT alignment models to predict the output labels. We have used SMT alignment models to align the abstract labels and trained CRF to predict the labels. We show that the state transition features improve the performance. Furthermore, we have compared the proposed method with two baseline approaches; Hidden Vector States (HVS) and baseline-CRF. The results show that for the F-measure the proposed...
Expert Finding in Bibliographic Network
, M.Sc. Thesis Sharif University of Technology ; Beigy, Hamid (Supervisor)
Abstract
Expert finding in bibliographic networks has received increasing attention in recent years. This task concerns with finding relevant researchers for a given topic. In this thesis, we propose a model to determine authority of authors who have participated in the Communities. This model has a little improvement over community based baseline model. However, due to the low performance of community based models, the proposed authority based model cannot improve the document based baseline models either. Therefore, we try to improve document based models, instead of community based models and have proposed two other models which are based on authors’ topic dominance for expert finding. Document...
Object Tracing Based on Detection and Learning
, M.Sc. Thesis Sharif University of Technology ; Jamzad, Mansour (Supervisor)
Abstract
Tracking is one of the old and still not thoroughly solved problems in machine vision. Its importance lies on its many applications. These applications vary from security surveillance to examining the motion pattern of atomic particles. There is not a tracker which has acceptable results in all situations, yet. A tracker faces many difficulties such as change in illumination and occlusion. In past, tracking was done by using filters or optical flows. By use of the advances in machine learning and pattern recognition, many models have been proposed to accomplish tracking by using these new learning methods. In this dissertation, we proposed a new tracking method which utilizes sparse...
The Pattern Recognition Methods in Combination with Nuclear Magnetic Resonance (NMR)Spectroscopy in Order to Develop a Metabolomic Approach to Breast Cancer Prognosis
, M.Sc. Thesis Sharif University of Technology ; Parastar Shahri, Hadi (Supervisor)
Abstract
The emerging field of “metabolomics” focuses on investigating into the changes of low-molecular-weight – less than 1500 Daltons – molecules, or metabolites, and it has significantly developed in the field of detecting diseases, particularly cancer in recent years. Regarding the importance of breast cancer (BC), especially among women, developing simple, trusted metabolic approaches are crucial. In the present work, utilizing multivariate class-modelling techniques combined to nuclear magnetic resonance (NMR) in order to predict breast cancer based on analyzing the blood serum of healthy and BC patients is presented. To do so, using 42 blood samples, 18 BC patients and 24 healthy individuals,...
Visual tracking using sparse representation
, Article 2012 IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2012, 12 December 2012 through 15 December 2012, Ho Chi Minh City ; 2012 , Pages 304-309 ; 9781467356060 (ISBN) ; Jourabloo, A ; Jamzad, M ; Manzuri Shalmani, M. T ; Sharif University of Technology
2012
Abstract
In this work we present a sparse dictionary learning method, specifically tuned to solve the tracking problem. Recently, sparse representation has drawn much attention because of its genuineness and strong mathematical background. In this paper we present an online method for dictionary learning which is desirable for problems such as tracking. Online learning methods are preferable because the whole data are not available at the current time. The presented method tries to use the advantages of the generative and discriminative models to achieve better performance. The experimental results show our method can overcome many tracking challenges
Discriminative Articulatory Models for Spoken Term Detection in Low-Resource Conditions
, M.Sc. Thesis Sharif University of Technology ; Sameti, Hossein (Supervisor)
Abstract
This thesis is focused on the spoken term detection system based on speech recognition in low resources conditions. A spoken term detection system is composed of two parts: speech recognition and search. In search of words, the method of proxy words is used as a basic approache to overcome the problem of OOV words. The main challenge in this thesis in the context of low resources, is poor training acoustic and language models and the small lexicon in speech recognition. Small lexicon increases the number of OOV words. In this thesis, two innovation has been proposed to improve the basic system. The first is training a bottleneck neural network for extraction the articulatory features of...