Coupling speech recognition and rule-based machine translation

Download
2008
Köprü, Selçuk
The objective of this thesis was to study the coupling of automatic speech recognition (ASR) systems with rule-based machine translation (MT) systems. In this thesis, a unique approach to integrating ASR with MT for speech translation (ST) tasks was proposed. The proposed approach is unique, essentially because it includes the rst rule-based MT system that can process speech data in a word graph format. Compared to other rule-based MT systems, our system processes both a word graph and a stream of words. Thus, the suggested integration method of the ASR and the rule-based MT system is more detailed than a simple software engineering practice. The second reason why it is unique is because this coupling approach performed better than the rst-best and N-best list techniques, which are the only other methods used to integrate an ASR with a rule-based MT system. The enhanced performance of the coupling approach was verified with experiments. The utilization of rule-based MT systems for ST tasks is important; however, there are some unresolved issues. Most of the literature concerning coupling systems has focused on how to integrate ASR with statistical MT rather than rule-based MT. This is because statistical MT systems can process word graphs as input, and therefore, the resolution of ambiguities can be moved to the MT component. With the new approach proposed in this thesis, this same advantage exists in rule-based MT systems. The success of such an approach could facilitate the efficient usage of rule-based systems for ST tasks.

Suggestions

Measurement based software process improvement
Ener, Aysun; Bilgen, Semih; Department of Electrical and Electronics Engineering (2007)
This thesis is a study on improving the software requirements management processes of embedded software department of a company. The literature on software process improvement and requirements engineering is reviewed. After determining the problems related to the current requirements management processes of the department, an improved process is proposed addressing these problems. The static process descriptions and the models of the current and improved requirements management processes are formed. A recen...
Investigation of the effects of structural characteristics of object-oriented software on fault-proneness
Gölcük, Halit; Bilgen, Semih; Department of Electrical and Electronics Engineering (2014)
This study investigates the effects of structural characteristics of object-oriented software, which are observable at the model level of the software developed by means of Unified Modeling Language (UML), on software quality, assessing quality in terms of fault-proneness. In the scope of this thesis study, real-time embedded software components developed by Aselsan, a leading defense industry company in Turkey, were analyzed. The correlation between software metrics measured from the UML models of the soft...
A systematic study of probabilistic aggregation strategies in swarm robotic systems
Soysal, Onur; Şahin, Erol; Department of Computer Engineering (2005)
In this study, a systematic analysis of probabilistic aggregation strategies in swarm robotic systems is presented. A generic aggregation behavior is proposed as a combination of four basic behaviors: obstacle avoidance, approach, repel, and wait. The latter three basic behaviors are combined using a three-state finite state machine with two probabilistic transitions among them. Two different metrics were used to compare performance of strategies. Through systematic experiments, how the aggregation performa...
Visual composition component oriented development
Öztürk, Murat Mutlu; Doğru, Ali Hikmet; Department of Computer Engineering (2005)
This thesis introduces a visual composition approach for JavaBeans components, in compliance with the Component Oriented Software Engineering (COSE) process. The graphical modeling tool, COSECASE, is enhanced with the ability to build a system by integrating domain-specific components. Such integration is implemented by defining connection points and interaction details between components. The event model of the JavaBeans architecture is also added to the capabilities.
Special index and retrieval mechanism for ontology based medical domain search engines
Kubilay, Mustafa; Baykal, Nazife; Department of Information Systems (2005)
This thesis focuses on index and retrieval mechanism of an ontology based medical domain search engine. First, indexing techniques and retrieval methods are reviewed. Then, a special indexing and retrieval mechanism are introduced. This thesis also specifies the functional requirements of these mechanisms. Finally, an evaluation is given by indicating the positive and negative aspects of mechanisms.
Citation Formats
S. Köprü, “Coupling speech recognition and rule-based machine translation,” Ph.D. - Doctoral Program, Middle East Technical University, 2008.