Browsing by Author "Hailemariam, Sebsibe (PhD)"

Now showing 1 - 6 of 6
  • No Thumbnail Available
    Item
    Amharic Sentence to Ethiopian Sign Language Translator
    (Addis Ababa University, 2014-06) Zegeye, Daniel; Hailemariam, Sebsibe (PhD)
    Sign languages that exist around the world are usually identified by the country where they are used such as Ethiopian sign language. Mostly, the communication among the hearing impaired people involves signs that stand for words by themselves. However, to make a sign language complete as a spoken language, the hearing impaired community around the world use manual alphabets for names, technical terms, and sometimes for emphasis. As there are different alphabets for different spoken languages such as Amharic, there are manual alphabets or finger spellings used by the deaf people. Therefore sign language in general is a tool that deaf communities use to communicate with each other. There is no problem when the communication is limited between the deaf, but they struggle to communicate with hearing people due to the language barrier. Using translators was the solution for filling the communication gap especially in Ethiopia, even if it has its own draw backs with respect to economy or privacy issue. Consequently, developing software which fills the communication gap between the deaf and hearing people is a best solution. This thesis contributes on the development of a model and system for Amharic sentence to Ethiopian sign language translator which accepts Amharic sentences, letters, or numbers, and outputs 3D animation of Ethiopian sign language based on the pre-lingual deaf grammar. The model bases on rule based machine translation approaches and the developed system has three basic components; the interface component, the back-end component, and the database component. The first component (front-end) acts as a bridge between the users and the back-end component. The back-end component has three modules; Amharic text analysis, natural language processing (NLP), and text-to-sign mapping. Amharic text analysis modules analyze Amharic sentence and pass Romanized sentence to the NLP module. The NLP module accepts the Romanized Amharic sentence and performs all language processing and return sentence in EthSL with including of morphological information. Then the final module (text-to-sign mapping) maps each word with the SiGML (sign script) and send to the interface component and the 3D avatar animation display the sign. In addition to enhance the quality of the translator we use a POS tagging which combine the previous work (naïve Byes classifier) and the new created one; using a brill tagging approach. x The translator performance evaluated into three classes; at sentences level, letter level, and number level and the result ranked into three categories; number of correctly translated sentences, number of understandable sentences, and number of wrong translations. All results without any errors were considered as correctly translated sentences. The results that conveyed meaning but not clear sense were considered as understandable sentences. But the results that did not covey meaning as well as sense were considered as wrong translations. Finally the system gave an accuracy of 58.77%, 75.76%, and 84% at sentence, letter, and number level respectively
  • No Thumbnail Available
    Item
    Amharic Sentence to Ethiopian Sign Language Translator
    (Addis Ababa University, 2014-06) Zegeye, Daniel; Hailemariam, Sebsibe (PhD)
    Sign languages that exist around the world are usually identified by the country where they are used such as Ethiopian sign language. Mostly, the communication among the hearing impaired people involves signs that stand for words by themselves. However, to make a sign language complete as a spoken language, the hearing impaired community around the world use manual alphabets for names, technical terms, and sometimes for emphasis. As there are different alphabets for different spoken languages such as Amharic, there are manual alphabets or finger spellings used by the deaf people. Therefore sign language in general is a tool that deaf communities use to communicate with each other. There is no problem when the communication is limited between the deaf, but they struggle to communicate with hearing people due to the language barrier. Using translators was the solution for filling the communication gap especially in Ethiopia, even if it has its own draw backs with respect to economy or privacy issue. Consequently, developing software which fills the communication gap between the deaf and hearing people is a best solution. This thesis contributes on the development of a model and system for Amharic sentence to Ethiopian sign language translator which accepts Amharic sentences, letters, or numbers, and outputs 3D animation of Ethiopian sign language based on the pre-lingual deaf grammar. The model bases on rule based machine translation approaches and the developed system has three basic components; the interface component, the back-end component, and the database component. The first component (front-end) acts as a bridge between the users and the back-end component. The back-end component has three modules; Amharic text analysis, natural language processing (NLP), and text-to-sign mapping. Amharic text analysis modules analyze Amharic sentence and pass Romanized sentence to the NLP module. The NLP module accepts the Romanized Amharic sentence and performs all language processing and return sentence in EthSL with including of morphological information. Then the final module (text-to-sign mapping) maps each word with the SiGML (sign script) and send to the interface component and the 3D avatar animation display the sign. In addition to enhance the quality of the translator we use a POS tagging which combine the previous work (naïve Byes classifier) and the new created one; using a brill tagging approach. x The translator performance evaluated into three classes; at sentences level, letter level, and number level and the result ranked into three categories; number of correctly translated sentences, number of understandable sentences, and number of wrong translations. All results without any errors were considered as correctly translated sentences. The results that conveyed meaning but not clear sense were considered as understandable sentences. But the results that did not covey meaning as well as sense were considered as wrong translations. Finally the system gave an accuracy of 58.77%, 75.76%, and 84% at sentence, letter, and number level respectively
  • No Thumbnail Available
    Item
    Improving Brill’s Tagger Lexical and Transformation Rule for Afaan Oromo Language
    (Addis Ababa University, 2013-02) Gizaw, Abraham; Hailemariam, Sebsibe (PhD)
    Natural Language Processing (NLP) refers to Human-like language processing which reveals that it is a discipline within the field of Artificial Intelligence (AI). However, the ultimate goal of research on Natural Language Processing is to parse and understand language, which is not fully achieved yet. For this reason, much research in NLP has focused on intermediate tasks that make sense of some of the structure inherent in language without requiring complete understanding. One such task is part-of-speech tagging, or simply tagging. Lack of standard part of speech tagger for Afaan Oromo will be the main obstacle for researchers in the area of machine translation, spell checkers, dictionary compilation and automatic sentence parsing and constructions. Even though several works have been done on POS tagging for Afaan Oromo, the performance of the tagger is not sufficiently improved yet. Hence, this thesis has developed Afaan Oromo POS tagger to improve Brill’s tagger lexical and transformation rule with sufficiently large training corpus. Accordingly, Afaan Oromo literatures on grammar and morphology are reviewed to understand nature of the language and also to identify possible tagsets. As a result, 26 broad tagsets were identified and 17,473 words from around 1100 sentences containing 6750 distinct words were tagged for training and testing purpose. From which 258 sentences are taken from the previous work. Transformation-based Error driven learning are adapted for Afaan Oromo part of speech tagging. Different experiments are conducted for the rule based approach taking 20% of the whole data for testing. A comparison with the previously adapted Brill’s Tagger is made. The previously adapted Brill’s Tagger shows an accuracy of 89.8% whereas the improved Brill’s Tagger result shows an accuracy of 95.6% which has an improvement of 5.8%. Hence, it is found that the size of the training corpus, the rule generating system in the lexical rule learner, and moreover, using Afaan Oromo HMM tagger as initial state tagger have a significant effect on the improvement of the tagger. Since there is only a few readymade standard corpuses, the manual tagging process to prepare corpus for this work was challenging and hence, it is recommended that a standard corpus is prepared. Keywords: Afaan Oromo, POS tagger, NLP, Brill’s Tagger
  • No Thumbnail Available
    Item
    Improving Brill’s Tagger Lexical and Transformation Rule for Afaan Oromo Language
    (Addis Ababa University, 2013-02) Gizaw, Abraham; Hailemariam, Sebsibe (PhD)
    Natural Language Processing (NLP) refers to Human-like language processing which reveals that it is a discipline within the field of Artificial Intelligence (AI). However, the ultimate goal of research on Natural Language Processing is to parse and understand language, which is not fully achieved yet. For this reason, much research in NLP has focused on intermediate tasks that make sense of some of the structure inherent in language without requiring complete understanding. One such task is part-of-speech tagging, or simply tagging. Lack of standard part of speech tagger for Afaan Oromo will be the main obstacle for researchers in the area of machine translation, spell checkers, dictionary compilation and automatic sentence parsing and constructions. Even though several works have been done on POS tagging for Afaan Oromo, the performance of the tagger is not sufficiently improved yet. Hence, this thesis has developed Afaan Oromo POS tagger to improve Brill’s tagger lexical and transformation rule with sufficiently large training corpus. Accordingly, Afaan Oromo literatures on grammar and morphology are reviewed to understand nature of the language and also to identify possible tagsets. As a result, 26 broad tagsets were identified and 17,473 words from around 1100 sentences containing 6750 distinct words were tagged for training and testing purpose. From which 258 sentences are taken from the previous work. Transformation-based Error driven learning are adapted for Afaan Oromo part of speech tagging. Different experiments are conducted for the rule based approach taking 20% of the whole data for testing. A comparison with the previously adapted Brill’s Tagger is made. The previously adapted Brill’s Tagger shows an accuracy of 89.8% whereas the improved Brill’s Tagger result shows an accuracy of 95.6% which has an improvement of 5.8%. Hence, it is found that the size of the training corpus, the rule generating system in the lexical rule learner, and moreover, using Afaan Oromo HMM tagger as initial state tagger have a significant effect on the improvement of the tagger. Since there is only a few readymade standard corpuses, the manual tagging process to prepare corpus for this work was challenging and hence, it is recommended that a standard corpus is prepared. Keywords: Afaan Oromo, POS tagger, NLP, Brill’s Tagger
  • No Thumbnail Available
    Item
    Raw Quality Value Classification of Ethiopian Coffee Using Image Processing Techniques: in the Case of Wollega Region
    (Addis Ababa University, 2011-11) Redi, Asma; Hailemariam, Sebsibe (PhD)
    Development of an automated computer vision system aiming in the establishment of technological and innovative approaches towards sample coffee bean raw quality value classification by extracting the relevant coffee bean features is the focal issue of this exploratory research. Of paramount significance in this regard is addressing the identified problems of the tedious and inefficient manual grading and sorting mechanisms of one of the most important agricultural products in Ethiopia, coffee. Prevalent sorting and classification approaches are characterized by subjective assessments of the features and nature of this huge economy representing crop, thereby influencing quality control and productivity aspects of the product. The major objective of the research spans extraction and selection of the important coffee bean morphological and color features that are useful for the purpose of classification of the raw quality grade level of sample coffee beans by designing, analyzing and testing a digital image processing model. The automated raw quality value classification experimentation comprised the analysis of images of washed coffee beans of varying grades from Wollega region, using major attributes of morphological structures (shape and size), and color features. Grades 2 – 9 of the coffee beans were available, providing a total of 27 samples, which yielded 324 sample images after a series of re-sampling measures of same into 12 sub-samples. The overall image processing work to develop models and depict trends for an efficient raw quality value classification involved sequential phases of image acquisition, image enhancement and segmentation, feature extraction, attribute selection, classification and performance evaluation. The Naïve Bayes, C4.5 and Artificial neural networks (ANN) were implemented for such classification purposes. A combined morphological and color features aggregate function dataset was used to develop the base model, though model attempts with separate features were conducted. Feed-forward multilayer perceptrons with two hidden layer and backpropagation algorithms are used in the ANN classifiers. Discretization of the raw quality value in to three interval classes was done to improve the performance of the model. 75% split evaluation technique was implemented for the Naïve Bayes and ANN classifiers as 10-foldcross validation evaluation techniques implemented in C4.5. Naïve Bayes classifier yielded higher model performance (82.72% correctly classified), followed by C4.5 (82.09%) and the ANN classifier (80.25%). Model robustness and sensitivity was analyzed by using perturbation analysis involving manipulations of model evaluation techniques and dataset characters. Alteration of number of beans in discretization and the use of different number of hidden layers constitute the trial modeling in this regard. Classification model was also run with various combinations of features of the coffee beans as listed with the attribute selection feature of Weka tool, where the final selection of the 21 features was done at a maximal model performance level for the Naïve Bayes and ANN classification approachs. C4.5 selected 10 features as it has its own attribute selection characteristics. An additional simulation was done with regression analysis for the sake of evaluation and trends analysis of the model outputs. A higher relation was resulted from this statistical approach between the raw quality values and the mentioned coffee bean features, supporting suitability and accuracy of dataset for classification in this research.
  • No Thumbnail Available
    Item
    Raw Quality Value Classification of Ethiopian Coffee Using Image Processing Techniques: in the Case of Wollega Region
    (Addis Ababa University, 2011-11) Redi, Asma; Hailemariam, Sebsibe (PhD)
    Development of an automated computer vision system aiming in the establishment of technological and innovative approaches towards sample coffee bean raw quality value classification by extracting the relevant coffee bean features is the focal issue of this exploratory research. Of paramount significance in this regard is addressing the identified problems of the tedious and inefficient manual grading and sorting mechanisms of one of the most important agricultural products in Ethiopia, coffee. Prevalent sorting and classification approaches are characterized by subjective assessments of the features and nature of this huge economy representing crop, thereby influencing quality control and productivity aspects of the product. The major objective of the research spans extraction and selection of the important coffee bean morphological and color features that are useful for the purpose of classification of the raw quality grade level of sample coffee beans by designing, analyzing and testing a digital image processing model. The automated raw quality value classification experimentation comprised the analysis of images of washed coffee beans of varying grades from Wollega region, using major attributes of morphological structures (shape and size), and color features. Grades 2 – 9 of the coffee beans were available, providing a total of 27 samples, which yielded 324 sample images after a series of re-sampling measures of same into 12 sub-samples. The overall image processing work to develop models and depict trends for an efficient raw quality value classification involved sequential phases of image acquisition, image enhancement and segmentation, feature extraction, attribute selection, classification and performance evaluation. The Naïve Bayes, C4.5 and Artificial neural networks (ANN) were implemented for such classification purposes. A combined morphological and color features aggregate function dataset was used to develop the base model, though model attempts with separate features were conducted. Feed-forward multilayer perceptrons with two hidden layer and backpropagation algorithms are used in the ANN classifiers. Discretization of the raw quality value in to three interval classes was done to improve the performance of the model. 75% split evaluation technique was implemented for the Naïve Bayes and ANN classifiers as 10-foldcross validation evaluation techniques implemented in C4.5. Naïve Bayes classifier yielded higher model performance (82.72% correctly classified), followed by C4.5 (82.09%) and the ANN classifier (80.25%). Model robustness and sensitivity was analyzed by using perturbation analysis involving manipulations of model evaluation techniques and dataset characters. Alteration of number of beans in discretization and the use of different number of hidden layers constitute the trial modeling in this regard. Classification model was also run with various combinations of features of the coffee beans as listed with the attribute selection feature of Weka tool, where the final selection of the 21 features was done at a maximal model performance level for the Naïve Bayes and ANN classification approachs. C4.5 selected 10 features as it has its own attribute selection characteristics. An additional simulation was done with regression analysis for the sake of evaluation and trends analysis of the model outputs. A higher relation was resulted from this statistical approach between the raw quality values and the mentioned coffee bean features, supporting suitability and accuracy of dataset for classification in this research.