Browsing by Author "Mesfin, Helina"

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Amharic Textual Entailment Classification Model Using Deep Neural Network
    (Addis Ababa University, 2020-12-09) Mesfin, Helina; Getahun, Fekade (PhD)
    Textual entailment can provide a semantic inference to natural language expression tasks that have meaning variability and it solves language ambiguity problems. Textual entailment classification task is to predict the given pairs of natural language expressions such that a human who reads the first element of a pair would most likely infer that the other element is entailment, neutral, or contradiction. In this work, we developed a textual entailment classification by using deep learning approach. Amharic is one of the most under resourced language, and has challenges in its linguistic levels. We developed an end to end solution as the approaches using deep Neural networks that can eliminate the underlying extensive feature engineering that shown traditional approaches for the development of Amharic Textual entailment classifier. The reverse side sentence matching model for Amharic textual entailment classification has five main layers. Which are word embedding, sentence embedding, and sentence matching, aggregation and prediction layers. Specifically, for the first word embedding layer, applied word vectors by attaching its sub word information that can represent the important features of Amharic words. Second In sentence embedding layer by leveraging bi-directional long short term memory network we are able to remember long sentence sequences of the dataset we prepared (pair of 8700 sentences) for Amharic Inference task. Third in matching layer we matched each time step of the hypothesis sentence against all time step of the premise by applying matching functions followed by a matching approaches, Our model produced encouraging result in contrast to the base line models by scoring 77% training and 72% of test accuracy,
  • No Thumbnail Available
    Item
    Amharic Textual Entailment Classification Model Using Deep Neural Network
    (Addis Ababa University, 12/9/2020) Mesfin, Helina; Getahun, Fekade (PhD)
    Textual entailment can provide a semantic inference to natural language expression tasks that have meaning variability and it solves language ambiguity problems. Textual entailment classification task is to predict the given pairs of natural language expressions such that a human who reads the first element of a pair would most likely infer that the other element is entailment, neutral, or contradiction. In this work, we developed a textual entailment classification by using deep learning approach. Amharic is one of the most under resourced language, and has challenges in its linguistic levels. We developed an end to end solution as the approaches using deep Neural networks that can eliminate the underlying extensive feature engineering that shown traditional approaches for the development of Amharic Textual entailment classifier. The reverse side sentence matching model for Amharic textual entailment classification has five main layers. Which are word embedding, sentence embedding, and sentence matching, aggregation and prediction layers. Specifically, for the first word embedding layer, applied word vectors by attaching its sub word information that can represent the important features of Amharic words. Second In sentence embedding layer by leveraging bi-directional long short term memory network we are able to remember long sentence sequences of the dataset we prepared (pair of 8700 sentences) for Amharic Inference task. Third in matching layer we matched each time step of the hypothesis sentence against all time step of the premise by applying matching functions followed by a matching approaches, Our model produced encouraging result in contrast to the base line models by scoring 77% training and 72% of test accuracy,
  • No Thumbnail Available
    Item
    The Effect of Leadership Styles on Job Satisfaction: The Case of Panafric Global PLC
    (Addis Ababa University, 2020-06) Mesfin, Helina; Mohammed, Abdurazak (PhD)
    The reason which initiates to do this study is that to show the effect of leadership styles on job satisfaction: the case of Panafric Global PLC. The participants of the study were employees of Panafric global PLC in Addis Ababa. In order to collect data, the researcher employed simple random sampling techniques to select participants of the study and total 104 questionnaires were distributed and 90 were properly filled and returned by using (MLQ) Multifactor Leadership Questionnaire and (JSS) Job Satisfaction Scale. In addition to analyze the data SPSS version 26 were used, reliability of questionnaire items had been tested using Cronbach's alpha, the study applied frequency and percentages, descriptive statistics and regression analysis. According to the descriptive statistics analysis all the three leadership styles are practical in Panafric Global PLC. The end result in the regression analysis bared that transformational leadership style has a positive significant effect on the dependent variable (Job Satisfaction). Transactional and Laissez faire leadership styles were found to have insignificant effect on job satisfaction. As a result the researcher recommends PAG to put an effort in employing transformative leaders because their characters increase employee job satisfaction, PAG should also work on improving job satisfaction factors in which the employees are less satisfied with, and conduct job satisfaction surveys regularly and take counteractive actions on areas that need improvement. Extensive training in leadership-related programs that will be conducted regularly is also recommended by the study