Information Sciences

Permanent URI for this collection

http://etd.aau.edu.et/handle/123456789/27

Browse

Now showing 1 - 20 of 717

An Academic Resource Centre in the University of Malawi: It’s Need and a Plan for Its Development, Together With Prototype Databases
(Addis Ababa University, 1993-06) Duncan Vote; Neelameghan A. (Professor)
The Academic Resource Centro (ARC) discussed in this thesis is an information facility designed to provide information support for the efficient and effective performance of the statutory and public service functions of the University of Malawi and its associated institutions and organizations including related government departments, pastorals, research centers etc. It is conceived as an information center forming an integral part of the university college and institutions associated with higher learning and research in Malawi. The ARC will utilize viable information technology in conjunction with manual methods. Pr-planning studies undertaken include: a review of trends in information technology (IT), a survey of a accessibility to IT in \ Malawi, an assessment of the existing information support systems of the University of Malawi and their inadequacies in relation to the information and data needs of the variety of users of the academic and research community and the related government and para statal organizations . Based on the findings, plans to develop the ARC and steps to implement the plans are proposed. The ARC is conceived as a networking of -viiinformation systems within the university and the associated institutions as well as of appropriate institutions in the country and abroad. The ARC plan outlines the requirements in terms of manpower, systems design and implementation. Libraries and information centers which could participate in the ARC network are mentioned. A set of integrated databases consisting of : bibliographic records; information on . \ curriculum development, academic prospectus etc; profiles of experts and institutions; of databases and information systems; of ongoing projects and researches in the university of Malawi, Government and other selected research institutions, is presented as prototypes for the databases to be developed at the ARC. Data entry guidelines are also provided. Training facilities for IT personnel are not adequate in the country and it has led to under utilization of equipment and heavy reliance on vendor service support for the systems. Some suggestions are made in overcoming this problem. Introduction of IT in libraries, documentation and information centres in the country is slowly gaining ground and currently is largely being applied in special -viiilibraries and to a certain extent in academic libraries as well. However, IT applications to generate information products and services is currently limited to word processing and in-house bibliographic database management. Emerging its, such as CD-ROM, networking and desktop publishing, are yet to be widely used in Malawi. The need for developing national databases to capture and disseminate information generated in the country is emphasized.
An Academic Resource Centre in the University of Malawi: It’s Need and a Plan for its Development, Together with Prototype Databases.
(Addis Ababa University, 1993-05) Duncan, Vote; Neelameghan, A. (Prof.)
The Academic Resource Centre (ARC) discussed in this thesis is an information facility designed to provide information support for the efficient and effective performance of the statutory and public service functions of the University of Malawi and its associated institutions and organizations including related government departments, parastatals, research centres etc. It is conceived as an information centre forming an i ntegral part of the university college and institutions associated with higher learning and research in Malawi. The ARC will utilize viable information technology in conjunction with manual methods. Pre-planning studies undertaken include: a review of trends in information technology (IT), a survey of accessibility to IT in Malawi, an assessment of the existing information support systems of the University of Malawi and their inadequacies in relation to the information and data needs of the variety of users of the academic and research community and the related government and parastatal organizations. Based on the findings, plans to develop the ARC and steps to implement the plans are proposed. The ARC is conceived as a networking of i nformat ion systems wi thi n t he university and the associated institutions as · well as of appropriate institutions in the country and abroad. The ARC plan outlines the requirements in terms of manpower, systems design and implementation. Libraries and information centres which could participate in the ARC network are mentioned. A set of integrated databases consisting of: bibliographic records; information on curriculum development, academic prospectus etc; profiles of experts and institutions; of databases and information systems; of ongoing projects and researches in the University of Malawi, Government and other selected research institutions, databases to is be presented developed as prototypes for the at the ARC. Data entry guideliness are also provided .Training fa c ilities for IT personnel are not adequate in the country and it has led to underutilization of equipment and heavy reliance on vendor service support for the systems. Some suggestions are made in overcoming this problem. Introduction of IT in libraries, documentation and information centres in the country is slowly gaining ground and currently is largely being applied in special libraries and to a certain extent i n academic libraries as well. However, IT applications to generate information products and services is currently limited to word processing and in-house bibliographic database management. Emerging Its, such as CD-ROM, networking and desktop publishing, are yet to be widely used in Malawi. The need for developing national databases to capture and disseminate information generated in the country is emphasized.
Accounting Information Support System with Particular Reference to Agency for the Administration of Rented Houses
(Addis Ababa University, 1995-06) Geda, Tessema; Tadesse, Taye (PhD)
The management process can be defined as the process of planning, organizing, staffing and cont r olling . The performance of a business can be measured on how well these func tions are being carried out. The main thing to be made is that better quality information which helps management in the process of managing a business. Accounting information, in this regard , plays a great role in: 1) Planning, because reporting information on past periods helps t he user to make predictions about future events . 2) Controlling , because budgets and standards are set, and performances are measured against these budgets and standards . 3) Decision making , because the reporting of possible outcomes based on alternative input allows the decision makers to select the best alternatives. The accounting function also acts as an over all control device for external consti cuent s such as external auditors , Inland Revenue Administra t ion and Other Government bodies . The result of the study reveals that accounting system of A. A. R.H. currently used is not capable of supporting t he management in r elation to investment and economic policy. Therefore , this thesis aims to furnish in prototype computer based accounting information to different level ofmanagers and to interested external users. The proposed computer-based accounting system for the accounting information system of A. A.R.H. emanates from the fact that : a) The existing semi-automated accounting system of A.A .R. H. has not been presented in a suitable form to help management. b) The traditional batch oriented processing of accounting creates a delay to provide timely information. Thus, using the database approach attempts have been made to design prototype accounting information system to be suitable for management in a timely fashi on . The thesis holds Accounting Concept, six chapters, t he Exist i ng the Int roduction part, Accounting Sy stem of A.A . R.H., the Proposed Accou~ t i n g System, System Operation and Implementation Plan and lastly Conclusion and Recommendations .
Accounting Information Support System with Particular Reference to Agency for The Administration of Rented Houses (A.A.R.H)
(Addis Ababa University, 1995-06) Geda, Tesema; Tadesse, Taye (PhD); Chowdhury, G.G. (PhD)
The management process can be defined as the process of planning, organizing, staffing and controlling. The performance of a business can be measured on how well these functions are being carried out . The main thing to be made is that better quality information which helps management in the process of managing a business. Accounting information, in this regard , plays a great role in: 1) Planning , because reporting information on past periods helps the user to make predictions about future events. 2) Controlling, because budgets and standards are set, and performances are measured against these budgets and standards. 3) Decision making, because the reporting of possible outcomes based on alternative input allows the decision makers to select the best alternatives . The accounting function also acts as an over all control device for external constituents such as external auditors , Inland Revenue Administration and Other Government bodies . The result of the study reveals that accounting system of A.A . R. H. currently used is not capable of supporting the management in relation to investment and economic policy. Therefore , this thesis aims to furnish in prototype computer based accounting information to different level of managers and to interested external users. The proposed computer-based accounting system for the accounting information system of A.A.R.H. emanates from the fact that: a) The existing semi-automated accounting system of A.A.R.H. has not been presented in a suitable form to help management. b) The traditional batch oriented processing of accounting creates a delay to provide timely information. Thus, using the database approach attempts have been made to design prototype accounting information system to be suitable for management in a timely fashion. The thesis holds six chapters, the Introduction part, Accounting Concept , the Existing Accounting System of A.A.R.H. , the Proposed Accounting System, System Operation and Implementation Plan and lastly Conclusion and Recommendations.
Adaptive E-Learning Design By Artificial Neural Network Techniques: A Case of Ethiopian Higher Learning Institution
(Addis Ababa University, 2010-06) Beyene, Melkamu; Lamnew, Workshet (PhD)
An e-learning system is expected to recognize the different learner characteristics, the complex learning process that can be influenced by learner characteristics such as previous knowledge, learning styles, background, etc. The system is also expected to analyze students need to use learning material and an order of presentation that depends upon their own characteristics and needs. More adaptivity is expected from e-learning systems since students need to be considered independent. The purpose of this study is to investigate and demonstrate the possibility of developing Adaptive e-learning model for Ethiopian higher learning institutions learners. In this research, an experiment was made to build a learner model for an adaptive e-learning model. Firstly, Information independent of the course like learner goals and background and experiences as well as domain dependent data like prior knowledge about the course and learner expectations from the course were assessed. Secondly, an experimental learning styles predictive model is built through neural network data mining modeling technique. From the analysis of the assessment in this study, Ethiopian higher learning institutions learners’ students have varying learning goals, learner background and experiences, preferences, learning styles as well as prior knowledge about the course and their expectations from the course. The learning style predictive model is experimented by neural network data mining technique from student learning style questionnaire that received from 1296 respondents. Fourteen variables were selected from the twenty variables for each model. From the total dataset, 80%, 10% and 10% of the data is used for training, validating and testing purpose respectively. Neural network model is built which can correctly classify 93.07%, 92.30%, 96.15% and 94.61% of the validation set for visual-auditory, sequential-global, activist-reflective, sensitive-intuitive and learning styles respectively. Lastly, an adaptive e-learning model prototype was designed.
Adoption and Challenges of Mobile Banking [Hello-Cash] System in Ethiopia: The Case of Cooperative Bank of Oromiya
(Addis Ababa University, 2017-06-07) Bayana Kumsa, Ebisa; Jemaneh, Ato Getachew
The incorporation of information system into an organization for the purpose of getting competitive advantage, easing workload, providing intangible (soft) work place and coping up with technological advancement has became an indispensable for organizations. Due to these many companies (for example banks) are getting advantage of information communication technology implementation like Mobile banking, Internet banking, ATM, etc. Accordingly Ethiopian commercial banks have implemented mobile banking system into their service system. However, with increased demand of users and technological advancements, the adoption of the mobile banking system has some challenges. This thesis aims to examine adoption of mobile banking system in the Ethiopia focusing on Cooperative bank of Oromiya with respect to the challenges which can influence the bank from taking advantage and expected benefits of mobile banking system derived by adopting the system. The study was conducted based on technology acceptance model (TAM) and innovative diffusion theory (IDT). Both qualitative and quantitative (mixed) research approach was used to answer the research questions that emerge through the review of existing literature and the context of the mobile banking system in Ethiopia and statistically analyzed data obtained from the survey questionnaire. The result of the study indicated that, drivers of mobile banking adoption are relative advantage, perceived ease of use and perceived usefulness. The study also identified the major challenges Ethiopian banking industry faces in the adoption of mobile banking system which are perceived risks, trust reliability, lack of legal frame and government support, lack of ICT infrastructure, electricity and telecommunications. The study suggests a series of measures which could be taken by the bank and government to address various challenges identified in the study. These measures were establishing a clear set of legal frame work on the use of technology in banking industry, supporting banking industry by investing on ICT, etc
Adoption Of E-Commerce Framework For Ethiopian Banks
(Addis Ababa University, 2017-06-08) Tefera Tekle, Emishaw; Mulugeta (PhD), Wondwossen
E-commerce, a relatively new concept for Ethiopian market, is giving competitive advantages across the globe in both developed and developing countries. This study is about adopting ecommerce framework for Ethiopian banks. The study has used technology organization environment (TOE) technology adoption model to identify the factors for e-commerce framework adoption for Ethiopian banks. It has also contextualized a questionnaire developed by Elizabeth and J. Michael (2004), in their research done for developing an e-commerce adoption model for developed countries Small and Medium Businesses. Following the survey results additional factors of e-commerce adoption are included on the TOE framework. Compatibility of the tailored e-commerce framework and external pressure are included as external factor of adoption to the existing TOE framework. Organizational support, organizational readiness, ease of use, usefulness, entrepreneurial orientation and perception of decision makers are also included as internal/organizational factors for e-commerce adoption. The survey responses are also used to perform strength, weakness, opportunity and threat (SWOT) analysis on each of the factors of e-commerce adoption. Based on the results a tailored e-commerce framework is proposed to suite the Ethiopian banks working environment by amending the national interoperability infrastructure–EthSwitch to interoperate among the member banks and the e-commerce application, 3-Domian secure (issuer, acquirer and interoperability), is interfaced with the merchant plug in at the merchant web site and rearranging the existing modules of the framework. As a result, the tailored e-commerce framework that is “close-controlled and close-boundary” will resolve the issues of e-commerce fraud, security related issues, settlement related issues, legislation and policy related issues. Other researchers will use the proposed framework as a startup to further study cross boarder e-commerce implementation in Ethiopia by widening the operating environment to accept major international standard cards such as the Visa and MasterCard
Adoption Of Information And Communication Technology In Public Administration In Oromia Region: The Case Of Bereh And Sendafa Woredas
(Addis Ababa University, 2017-06-05) Asefa, Girma; Lessa (PhD), Lemma
Information Communication Technology (ICT) has become a significant tool to facilitate human activity that has made contributing to the countries’ on economy and social welfare. As extant literature reveal, the application of ICTs in the public administrations is basically affected by the organizations context, technological context and environmental context factors. Purpose of this study was to identify the challenges and contextual factors that drive information and communication technology adoption in Bereh and Sendafa Woredas public administrations. To achieve objective a qualitative and quantitative approaches were conducted with a survey that focused on ICT uses, its challenges and contextual factor that drive ICT in the public administrations. The quantitative survey study was conducted on 230 respondents on both Woredas and the qualitative key informant interview. The data from both sources were combined and analyzed to get a view of the current situation. The findings show that the public administrations are mainly hindered by a group of challenges related to strategy design on ICT tools challenges for instances infrastructural, standard Internet connectivity design issues and the forces that drive the ICT adoption also ICT awareness creation among the top managers. Possible actions for management intervention are also forwarded based on the key findings
Afaan Oromo Morphological Analysis a Hybrid Approach
(Addis Ababa University, 2021-12-13) Genna, Kedir; Meshesha, Million (PhD)
This study provides relatively detailed information on developing Afaan Oromo morphological analysis system. Morphological analyzer decomposes words into its components called morphemes and annotates those morphemes with grammatical information. Although the module uses machine-learning approach on morphological analysis, it used rule-based approach to segments words into its small components, morphemes. The developed prototype focused on inflectional forms of nominals (nouns and adjectives) and verbs since the two words classes are mostly the ones that undergo inflection, they determine the inflectional characteristics of the language. The protype was developed using python programming and Hidden Markov Model (HMM). The Viterbi algorithm is used to encode the HMM model. Then, the prototype was trained and tested using representative data. A corpus of size 4,320 nouns and 3,780 verbs are used to train the HMM model. Then the performance of the analyser was tested using 480 nouns and 420 verbs. Generally, the accuracy of the analyzer for nouns and verbs is 84.6 % and 82.9% respectively. The result of the experiment was quite satisfactory, which can be improved by incorporating simple grammatical constraints and contextual information (including information encoded in tonal system) to minimize the ambiguities, words root database to reduce errors during morphemes identification and additional data to emphasis the initial probability of the model. The key limitations in this effort are limited funding opportunities, scarcity gold standard and balanced annotated data sets and inherently multiple sources of ambiguity of the language at different levels.
Afaan Oromo Text Retrieval System
(Addis Ababa University, 2012-06) Gutema, Gezehagn; Meshesha, Million(PhD)
This study is mainly intended to make possible retrieval of Afan Oromo text documents by applying techniques of modern information retrieval system. Information retrieval is a mechanism that enables finding relevant information material of unstructured nature that satisfies information need of user from large collection. Afaan Oromo text retrieval developed in this study has indexing and searching parts. Vector Space Model of information retrieval system was used to guide searching for relevant document from Oromiffa text corpus. The model is selected since Vector space model is the widely used classic model of information retrieval system. The index file structure used is inverted index file structure. For this study text document corpus is prepared by the researcher encompassing different news article and experiment is made by using 9(nine) different user information need queries. Various techniques of text pre-processing including tokenization, normalization, stop word removal and stemming are used for both document indexing and query text. The experiment shows that the performance is on the average 0.575(57.5%) precision and 0.6264(62.64%) recall. The challenging tasks in the study are handling synonymy and polysemy, inability of the stemmer algorithm to all word variants, and ambiguity of words in the language. The performance the system can be increased if stemming algorithm is improved, standard test corpus is used, and thesaurus is used to handle polysemy and synonymy words in the language.
Afaan Oromo-English Cross-Lingual Information Retrieval (CLIR): a Corpus Based Approach
(Addis Ababa University, 2011-06) Bekele, Daneal; Teferi, Dereje(PhD)
The goal of Cross Language Information Retrieval (CLIR) is to provide users with access to information that is in a different language from their queries. It has the ability to issue a query in one language and retrieve documents in another. This is achieved by designing a system where a query in one language can be compared with documents in another. Afaan Oromo is one of the major languages that are widely spoken and used in Ethiopia. Despite the fact that Afaan Oromo has a large number of speakers, little effort has been put in conducting researches which aim at making English documents available to Afaan Oromo speakers. This study is, therefore, an attempt to develop Afaan Oromo-English CLIR system which enables Afaan Oromo native speakers to access and retrieve the vast online information sources that are available in English by writing queries using their own (native) language. In this study, the development of a corpus-based CLIR system which makes use of wordbased query translation for Afaan Oromo-English language pairs and evaluation of the system on a corpus of test documents and queries prepared for this purpose is described. This approach requires the availability of parallel documents hence such documents are collected from Bible chapters, legal and some available religious documents. Evaluation of the system is conducted by both monolingual and bilingual retrievals. In the monolingual run, the Afaan Oromo queries are given to the system and Afaan Oromo documents are retrieved while in the bilingual run the Afaan Oromo queries are given to the system after being translated into English to retrieve English documents. For the bilingual run translation of Afaan Oromo queries into their English equivalent is done by using bilingual dictionary constructed from the collected parallel corpora. The performance of the system was measured by recall and precision. In the first phase of the experimentation, the maximum average precision value of 0.421and 0.304 are obtained for the Afaan Oromo and English documents respectively. The second phase of experimentation performs slightly better than the first. Maximum average precision value of 0.468 and 0.316 are obtained for the Afaan Oromo and English documents respectively. Therefore, with the use of large and cleaned parallel Afaan Oromo-English document collections, it is possible to develop CLIR for the language pairs.
Agricultural Information Network For Ethiopia : Need, Functions and Implementation Strategy
(Addis Ababa University, 1992-06) Kebede, Gashaw; Neelameghan, A. (Prof.)
The relevance and viability of cooperative approach by forming a network of existing information service units in the country to address commonly faced shortcomings in agricultural information provision was assessed and discussed. A review of literature on various aspects of information ne tworking was made mainly to draw up a general framework and basic pri nciples essential to asse ss viability, to determine possible and viable areas of cooperation and to establish the particular type of net work required. A preliminary survey on problems, resource capability and attitude to networking on the existing information service units in Ethi opia using questionnaire supported by selected interview was conducted. The results revealed shortages in information sources, skilled personnel, and equipment and facility; and cumbersome organizational structures are widespread. standardization and bibliographic control tools are also a bsent. Local publications are neglected areas. Financial resource limitations are major problems. The information services provided are limited to reading and lending services by large. All these are constraints in the improvements . of the services immedi tely. staff will i ngness to appr oach , the" existing problems cooperatively was high. Also surveyed with a different questionnaire were agricult ural information users of the surveyed information service units so as to assess their reaction to and opinions about the available servi ces which t he ne t wor k could t ake into cons i de r ation as i t s ultimate goal. Al t hough at present books are t he most used, journals and loca l pUblica t ions are rep o r ted t o be in great demand. Liter ature s e a r ch, phot ocopying, doc ument delivery are a lso requi red. The ma jority are dissati s f i ed with their in forma t ion servi ce units beca us e their information ne eds are not met. However, many seem to appreciate a cooper ative approach to the ser vices although at present many are less frequent us ers of other similar information units in the country. Taking into consideration what is affordable by the existing units on the one hand and the need to addr ess t he pressing problems on the other, feasi ble areas for a network were identified ,namely, establishing union c atalogues of holdings and list of local publications, limited interl ibr ary loan, t raining and standardization with focus on laying the g r ound for further wider cooperation leading towar ds meeting the expressed as well as generally r equired needs of users and to assist the services achieve better standards of service and r esource base. Recommendations are made to initiate the network and make it operational.
Agricultural Information Network For Ethiopia : Needs, Functions and Implementation Strategy
(Addis Ababa University, 1992-06) Kebede, Gashaw; Lancaster, F.W.Prof.
The relevance e and viability of cooperative approach by forming a network of existing information service units in the country to address commonly faced shortcomings in agricultural information provision was assessed and discussed. A review of literature on various aspects of information networking was made mainly to draw up a general framework and basic principles essential to assess viability, to determine possible and viable areas of cooperation and to establish the particular type of network required. A preliminary survey on problems, resource capability and attitude to networking on the existing information service units in Ethiopia using questionnaire supported by selected interview was conducted. The results revealed shortages in information sources, skilled personnel, and equipment organizational structures are and facility; and cumbersome widespread. Standardization and bibliographic control tools are also absent. Local publications are neglected areas. Financial resource limitations are major problems. The information services provided are limited to reading and lending services by large. All these are constraints in the improvements of the services immediately. Staff willingness to approach the existing problems cooperatively was high. Also surveyed with a different questionnaire were agricultural information users of the surveyed information service units so as to assess their reaction to and opinions about the available services which the network could take into consideration as its ultimate goal. Although at present books a re the most used, journals and local publications are reported to be in great demand. Literature search, photocopying, document delivery are also required. The majority are dissatisfied with their information service units because their information needs are not met. However, many seem to appreciate a cooperative approach to the services although at present many are less frequent users of other similar information units in the country. Taking into consideration what is affordable by the existing units on the one hand and the need to address the pressing problems on the other, feasible areas for a network were identified ,namely, establishing union catalogues of holdings and list of local publications, limited inter library loan, training and standardization with focus on laying the ground for further wider cooperation leading towards meeting the expressed as well as generally required needs of achieve better standards users and of service to assist the services and resource base. Recommendations are made to initiate the network and make it operational.
Amharic - English cross-lingual information retrieval (Cllr): A corpus based approach
(Addis Ababa University, 2009-08) Tesfaye Aynalem; Abebe Ermias (Ato)
Amharic is the official working language of the Federal Democratic Republic of Ethiopia. On the other hand, English serves as medium of instruction and communication in educational centers, working language in governmental and nongovernmental organizations in Ethiopia. Thus, experimenting on the applicability of a cross language information retrieval system for Amharic-English that can break the language barrier is important. This research is conducted to break the language barrier that users face in obtaining and using documents prepared in Amharic and English. Amharic is the official working language of the Federal Democratic Republic of Ethiopia. On the other hand, English serves as medium of instruction and communication in educational centers, working language in governmental and nongovernmental organizations in Ethiopia. Thus, experimenting on the applicability of a cross language information retrieval system for Amharic-English that can break the language barrier is important. This research is conducted to break the language barrier that users face in obtaining and using documents prepared in Amharic and English. The method that is employed to conduct the experimentation is a corpus-based approach. This approach requires availability of a large volume of parallel documents prepared in Amharic and English. The documents that were collected to conduct this research are news articles and legal items.The performance of the system was measured by precision and recall. At the first phase of the experimentation, precision values were very low - the highest being 0.2 and 0.3 for Amharic and English respectively. This was due to the index term list which could not fully represent the documents used for the experimentation. The process of indexing removed important terms from index list which resulted in lack of documents to be retrieved for most of the queries. Thus, the index list was modified, i.e., all the terms which occur in the corpus with the exception of stop words were used. This showed the increase in precision values - the highest being 0.36 and 0.33 for Amharic and English documents respectively. Therefore, with the use of sufficiently large and cleaned parallel Amharic-English document collection, it is possible to develop a cross language information retrieval for the language pairs.
Amharic Connected Word Speech Recognition System for Mobile Phones
(Addis Ababa University, 2017-10-02) Dagne, Bewunetu; Yifru (Ph. D), Martha
This study investigated ways of integrating an Amharic Automatic speech recognition (ASR) system on mobile phones and demonstrated the possibility of using a connected word Amharic ASR system that can be used to command and control mobile phone devices – devices which currently have become not only a valuable means of communication, but also a common computing device that we carry everywhere. To this end, CMUSphinx’s Pocketsphinx is used to build a connected word, offline, small vocabulary and speaker dependent Amharic ASR system. For the fact that CMUSphinx system does not support whole word models rather word-dependent phone models, in this research work, two distinct acoustic models namely, word-dependent phone (WDP) and word-dependent CV syllable (WDCVS) models are built. And a total of 36 words are used in both models to recognize the Amharic digits from 0 to 100 and a limited set of command phrases, spoken in a connected manner. A prototype Android application is also developed and used to integrate the developed acoustic models with an Android phone. To model the sequence of words acceptable in the prototype application, three different context free grammar files are created and used. The approach used in implementing the recognizer is embedded speech recognition, or simply ESR, using the Pocketsphinx tool – an open source speech recognition toolkit optimized to run on embedded devices. The methodology employed to develop the recognizer is the most popular statistical model which is the Hidden Markov Model. In this study, two categories of performance evaluations are carried out. The first, Category I, is conducted to determine the effect the three model types i.e. continuous, semi-continuous and PTM, have on the two models i.e. WDP and WDCVS, and the second, Category II, is conducted to determine the best of the two models on a mobile phone using the prototype application. Hence, in the second category of evaluations, the best recognition accuracies found for the two models are, 98.07% for WDCVS model and 97.58% % for the WDP model. Thus, according to the results gained, it is highly promising to fully deploy Amharic ASR systems to command, control and perform other activities on mobile phones using Amharic language.
Amharic Document Image Retrieval Without Explicit Recognition
(Addis Ababa University, 2009-06) Worku, Mesfin; Meshesha, Million (PhD); Inkpen, Diana (PhD)
Retrieval of the stored information is a key issue. Especially image retrieval needs an emphasis , because the nature of the data is complex and difficult to retrieve . There are many problems to be studied in the area of image retrieval. From these , Document Image Retrieval is one of the issues that have to be given attention Document retrieval can use either a textual-based retrieval system or animate based retrieval system. Document image retrieval system can also be done in two ways: recognition-based document image retrieval or document image retrieval without explicit recognition Currently , little has been done on the Amharic document retrieval systems . The Amharic text retrieval systems which are covered by the researchers considered limited Amharic documents that are available only in hardcopy format The proposed system incorporates document images and user queries . The document image is preprocessed , segmented at word le vela and the feature of each word is extracted . Then the textual query is rendered to convert into an image query, preprocessed , segmented and the feature is extracted . The technique used for feature extraction considers the word shape analysis . The extracted feature of the image query is matched with the feature of the document images , at word level using Euclidean and cosine similarity measures . Finally relevant document images are retrieved in ranked order in response to the given query. To verify the validity of the approach proposed , experiment is carried out on 121 scanned Amharic documents that are selected from printed legal documents and news items. The data retrieval effectiveness is measured using retrieval measures such as precision , recall and F-Score . The experimental results confirmed the validity of the model for retrieving relevant document images from the collection of scanned document images.
Amharic Question Answering for Factoid and List Questions Using Machine-Learning Approaches
(Addis Ababa University, 2019-02-04) Getachew Medhanit; Abebe Ermias (Ato)
Question answering is a system that allows users to ask questions about some topic in natural language and give exact answers by retrieving answers from collection of documents. Its main aim is to assist human to get exact answers to questions they ask. In addition, it avoids going through many documents to find a single answer to their questions. There are two types of questions in QA namely factoid and non-factoid questions. The first one comprises of what, where, when, who questions and the second one deals with list, definition, acronym, how questions. The focuses of this study are factoid and list questions. There are some researches conducted previously on question answering. Most of the researches used only SVM algorithm for question classification and any of them did not make use of named entity recognizer for answer extraction. In this study an attempt is made to design a list and factoid question answering using machine learning approach and an answer extraction that makes use of NER. This research is a closed domain QA for Amharic that focuses on Ethiopian history. It has three components. Question classification for identifying the types of questions which is done using two algorithms; HMM and SVM, passage retrieval that is performed by selecting the relevant sentences using sentence-level retrieval and answer extraction component selects answers from the top ranked sentences using a NER which is developed for this research. Factoid questions are answered by using key words matching and extraction using the NER from the question and the list questions are answered by using co-occurrence of answer types and candidate answers in a text. The study achieved an F-measure of 73% using the SVM classifier for question classification and an F-measure of 65% was achieved using the HMM classifier for question classification. From the result we achieved, we realized that question classification using SVM has a better answer extraction performance than the HMM. In addition, the use of NER tool helped answer extraction in getting exact answers.
Amharic Speech Search Using Text Word Query
(Addis Ababa University, 2022-01-20) Mezgebu, Getnet; Teferra, Solomon (PhD)
In a world where more than 7000 languages are spoken and the processing and storage power of machines are maximized, many speech data are produced every day using different languages. Amharic is one of the languages spoken in the East African country, Ethiopia. Searching for a particular spoken word with its respective time frame inside a given audio file is a challenge. The main objective of this research was to investigate the development of a system that can search speech and locate utterance with its respective time from the Amharic audio file by using Amharic text word query. In this study, the researchers followed an experimental research methodology. To meet the research objective, we have conducted an experiment to get the optimal segmentation for which we can achieve the lowest WER of the ASR system that decodes the segmented speech. We have also experimented on the use of previously developed speech corpus, which is in a broadcast domain, together with the in-domain speech corpus, which is the Bible domain; we have developed for our research. The performance of the ASR obtained by combining the two different domains shows a better WER than that of using only LVCSR. On the other hand, the comparison of automatically segmented speech with automatic sentence-like segmentations shows closer WER with the manually (by hand) segmented speech. Using the optimal automatic segmentation and LVCSR, the researchers developed a text-based STD which can locate the time interval upon which the query term is located. The text-based STD was developed with ASR having a WER of 53% and 46 % using LVCSR and by combining LVCSR and Bible speech respectively. The developed STD has a Graphical User Interface (GUI) which will make searching easy to use and friendly. We found that the performance of ASR affects the performance of STD since not all terms are fully transcribed.
Amharic Spelling Error Detection and Correction System: Morphology-Based Approach
(Addis Ababa University, 2020-09-10) Shimelis, Mariawit; Melese, Michael (PhD)
Nowadays, it is a common practice to notice spelling errors in typed Amharic documents. As Amharic is the official working language of Ethiopia and the second most spoken Semitic language in the world, the need to have an Amharic spelling error detection and correction system is evident. Previous attempts are made to develop a spell checker for Amharic. These works have attempted to use existing approaches likes metaphone and edit distance algorithms. However, these approaches are designed for languages which have a simple morphology like English. Moreover, unlike Amharic, in other languages distance between words is not dependent on the family and order of characters. As a result, using these approaches for a language with complex morphology like Amharic will not give the anticipated result. Similarly, using existing morphological analyzers for computational morphology is attempted in other works. Though the analyzers were reported to work with reasonable accuracy for valid words, their output for misspelled words is not clear. Accordingly, this study attempts to investigate the possibility of using morphology-based approach to design and develop an Amharic typing error detection and correction system for non-word errors. Design science methodology is employed in this study. It involves six activities namely, problem identification and motivation, defining objectives, design and development, demonstration, evaluation and communication. To carry out the experiment 717 morphological rules are defined, 2398 stem words selected from each category of root words are stored and the system has been tested with 1724 words selected from different derivational and inflectional categories. A prototype is developed using python programming language and it uses three knowledge bases which are stored in csv format. To evaluate the system, evaluation metrics precision, recall and predictive accuracy are used. The experimental results show 96% Lexical Recall, 89% Error Recall, 99% Lexical Precision, 70% Error Precision, 95% Predictive Accuracy and 70% corrections are generated for correctly identified invalid words. This shows that the system has high accuracy in flagging words as valid/ invalid and needs some improvement in suggestion generation. The system gives a good accuracy for selected words (with complex morphology) which are representative of words in the languages. Accordingly, it is concluded that the system is capable of detecting and correcting errors as long as the correct rule definition is defined and the corresponding stem is found inside the dictionary. It is also concluded that by applying the algorithms proposed for morphological analysis and distance calculation, morphology-based approach is suitable for Amharic spell checking than other approaches. For future works, improving rule definitions by including word classes, handling exceptions, including additional spell checker functionalities, expanding the work to include real-word errors and applying the proposed architecture for Amharic-English translation systems are recommended.
Amharic Text retrieval: an Experiment using Latent Semantic Indexing (LSI) with Singular Value Decomposition (SVD
(2003-07) Hailemeskel, Tewodros; Amsalu, Saba; Lisanu, Kibur
The increase in the amount of electronic information has caused increasing need for efficient information retrieval techniques. Most techniques to retrieving textual materials from databases depend on exact term match between terms in user’s query and terms by which documents are indexed. However, since there are usually many ways to express the same concept, the terms in the user’s query may not appear in a relevant document. Alternatively, many words can have more than one meaning. Due to these facts term matching methods are likely to miss relevant documents and also retrieve irrelevant ones (Dumais, 1992; Berry, Dumais & Letsche, 1995). The Latent Semantic Indexing (LSI) technique of information retrieval can partially handle these problems by organizing terms and documents into a “semantic” structure more appropriate for information retrieval. This is done by modeling the inherent higher-order pattern in the association of terms with documents. In this thesis, the potential of LSI approach in Amharic text retrieval is investigated. 206 Amharic documents and 25 queries were used to test the approach. Automatic indexing of the documents resulted in 9256 unique terms which are not in the stop-word list used for the research. A 110-factor SVD of the term by document matrix is used for indexing and retrieval. Finally, the performance of the LSI approach is compared with the standard vector space. Except at one standard recall level (0.80) precision of the LSI approach was above that of the standard vector space.

Browse

Browsing Information Sciences by Title

Results Per Page

Sort Options