English-Wolaytta machine translation system using statistical approach

The translation of foreign language texts by computers was one of the first tasks that the pioneers of computing and artificial intelligence set themselves. Machine translation is again becoming an important field of research and development as the need for translations of technical and commercial documentation is growing beyond the capacity of the translation profession. Abstract Machine translation is a technology for the automatic translation of text or speech from one natural language to another. Since there is a need for translation of sentences between English-Wolaytta language to make available the English documents in Wolaytta language and minimize the language barrier. Thus, this study in the development of a English-Wolaytta machine translation system using statistical approach. In order to achieve the objective of this research work, 30,000 bilingual corpus is collected from spiritual domain and 39,893 monolingual corpus from different sources. And also prepared in a format suitable for use in the development process (normalization, tokenization, lower-case and clean) and classified as training, tunning and testing set. Aligned parallel sentences manually and used freely available tools for the different purposes such as SRILM toolkit for language model, MGIZA++ align the corpus at word level by using IBM models (1-5), Decoding has been done using Moses, and Ubuntu operating system which is suitable for Moses environment has been used. In addition, unsupervised morpheme segmentation tool Morfessor is used for segmentation of Wolaytta text. The experiments were taken separately, one for the unsegmented and the other for segmented corpus. The parallel sentences divided by 5,000, 10,000, 15,000, 20,000, 25,000 and 30,000. The unsegmented corpus performs BLEU score of 4.91%, 6.30%, 7.21%, 7.60%, 7.96% and 8.46% used the above divided parallel sentences. The segmented corpus performs BLEU score of 9.83%, 11.38%, 12.70%, 12.77%, 12.93% and 13.21% used the above divided parallel sentences. Its performance improved by increased the size of the corpus and segmented parallel sentences. Base on the experiments done, the researcher observed that there will be a better performance when increase the size of the corpus and morphological segmentation. Therefore future research should focus to further improve the performance of the system increase the size of the corpus and morphological segmentation. List of Tables List of Figures Acronyms and Abbreviations CHAPTER ONE 1. INTRODUCTION 1.1. Introduction 1.2. Background 1.3. Statements of the Problem 1.4. Objectives of the Study 1.4.1. General Objective 1.4.2. Specific Objectives 1.5. Methodologies 1.5.1 Literature Review 1.5.2. Data Collection 1.5.3. Tools and Techniques 1.5.4. Evaluation 1.6. Scope and Limitations of the Study 1.6.1. Scope of the Study 1.6.2. Limitations of the Study 1.7. Contribution of the Study 1.8. Organization of the Thesis CHAPTER TWO 2. WOLAYTTA LANGUAGE 2.1. Introduction 2.2. Overview of Wolaytta Language 2.3. Morphology 2.3.1. Morphological Analysis 2.3.2. Morphological Synthesis 2.4. Morphology of Wolaytta 2.4.1. Personal Pronouns 2.4.2. Subject Verb Agreement 2.4.3. Nouns 2.4.4. Gender 2.4.5. Number 2.5. Wolaytta Language Writing System 2.6. Wolaytta Language Sentence Structure 2.7. Articles 2.8. Punctuation Marks 2.9. Conjunctions CHAPTER THREE 3. LITERATURE REVIEW 3.1. Introduction 3.2. Machine Translation (MT) 3.3. Approaches of Machine Translation 3.3.1. Statistical Machine Translation (SMT) Language Modeling Translation Modeling Decoder 3.3.2. Rule Based Machine Translation (RBMT) 3.3.3. Example Based Machine Translation (EBMT) 3.3.4. Hybrid Machine Translation (HMT) 3.3.5. Neural Machine Translation (NMT) 3.4. Evaluation of Machine Translation 3.5. Related Works 3.5.1. English–Afaan Oromo Machine Translation: An Experiment Using Statistical Approach 3.5.2. Bidirectional English-Amharic Machine Translation: An Experiment using Constrained Corpus 3.5.3. Preliminary Experiments on English-Amharic Statistical Machine Translation (EASMT) 3.5.4. Bidirectional English–Afaan Oromo Machine Translation Using Hybrid Approach 3.5.5. English-Tigrigna Factored Statistical Machine Translation 3.5.6. Bidirectional Tigrigna-English Statistical Machine Translation CHAPTER FOUR 4. DEVELOPMENT OF ENGLISH-WOLAYTTA SMT 4.1. Introduction 4.2. Architecture of the English-Wolaytta SMT 4.3. Corpus Collection and Preparation 4.3.1. Preliminary Preparation 4.3.2. Bilingual Corpus 4.3.3. Monolingual Corpus 4.3.4. Language Model 4.3.5. Translation Model 4.3.6. Decoding 4.4. Software’s CHAPTER FIVE 5. EXPERIMENT 5.1. Introduction 5.2. Experiment 5.2.1. Experiment-I: Unsegmented Corpus Set 5.2.2. Experiment-II: Segmented Corpus Set 5.3. Discussion CHAPTER SIX 6. CONCLUSION AND RECOMMENDATION 6.1. Conclusion 6.2. Recommendation 7. References This textbook on machine translation of language deals with the fundamental computational and linguistic aspects of the subject. The book also offers coverage of current knowledge in the field.