Browsing by Author "Bekele, Emebet"

Now showing 1 - 4 of 4
  • No Thumbnail Available
    Item
    Design and Development of Amharic-English Cross Language Question Answering System
    (Addis Ababa University, 2019-10-06) Bekele, Emebet; Getahun, Fekade (PhD)
    Most of web documents are published in English. Due to this reason, different information retrieval systems that retrieve English documents are developed by different researchers. And, Web users who do not know English are unable to access those systems in their native language. To enable Web users to access web documents written in a different language, a cross-language information retrieval is one of the solutions. So that, a question answering system is one of a practical application of information retrieval. Developing a cross lingual question answering system is essential to enable user to ask a question in a language different than the language in which documents are written. We used a statistical machine translation-based approach for Amharic-English cross language question answering. In this research work, we have designed architecture of Amharic-English cross language question answering. In doing so, we have developed a statistical machine translation system for translating user question. Also, to make the system more effective, we developed an Amharic named entity tagger with an algorithm of maximum entropy. And by using this system we make a semantic based indexing; it is a great technique to increase precision of the system and pinpointing an answer. To evaluate the overall system, precision and recall metrics are used. The Experimental result obtained shows that for Amharic-English cross lingual retrieval we got a result of 72% of precision and recall of 79% and for English-Amharic cross lingual retrieval got a result of 65% of precision and recall of 70%.
  • No Thumbnail Available
    Item
    Design and Development of Amharic-English Cross Language Question Answering System
    (Addis Ababa University, 10/6/2019) Bekele, Emebet; Getahun, Fekade (PhD)
    Most of web documents are published in English. Due to this reason, different information retrieval systems that retrieve English documents are developed by different researchers. And, Web users who do not know English are unable to access those systems in their native language. To enable Web users to access web documents written in a different language, a cross-language information retrieval is one of the solutions. So that, a question answering system is one of a practical application of information retrieval. Developing a cross lingual question answering system is essential to enable user to ask a question in a language different than the language in which documents are written. We used a statistical machine translation-based approach for Amharic-English cross language question answering. In this research work, we have designed architecture of Amharic-English cross language question answering. In doing so, we have developed a statistical machine translation system for translating user question. Also, to make the system more effective, we developed an Amharic named entity tagger with an algorithm of maximum entropy. And by using this system we make a semantic based indexing; it is a great technique to increase precision of the system and pinpointing an answer. To evaluate the overall system, precision and recall metrics are used. The Experimental result obtained shows that for Amharic-English cross lingual retrieval we got a result of 72% of precision and recall of 79% and for English-Amharic cross lingual retrieval got a result of 65% of precision and recall of 70%.
  • No Thumbnail Available
    Item
    Design and Development of Amharic-English Cross Language Question Answering System
    (Addis Ababa University, 2019-10-10) Bekele, Emebet; Getahun, Fekade (PhD)
    Most of web documents are published in English. Due to this reason, different information retrieval systems that retrieve English documents are developed by different researchers. And, Web users who do not know English are unable to access those systems in their native language. To enable Web users to access web documents written in a different language, a cross-language information retrieval is one of the solutions. So that, a question answering system is one of a practical application of information retrieval. Developing a cross lingual question answering system is essential to enable user to ask a question in a language different than the language in which documents are written. We used a statistical machine translation-based approach for Amharic-English cross language question answering. In this research work, we have designed architecture of Amharic-English cross language question answering. In doing so, we have developed a statistical machine translation system for translating user question. Also, to make the system more effective, we developed an Amharic named entity tagger with an algorithm of maximum entropy. And by using this system we make a semantic based indexing; it is a great technique to increase precision of the system and pinpointing an answer. To evaluate the overall system, precision and recall metrics are used. The Experimental result obtained shows that for Amharic-English cross lingual retrieval we got a result of 72% of precision and recall of 79% and for English-Amharic cross lingual retrieval got a result of 65% of precision and recall of 70%.
  • No Thumbnail Available
    Item
    The Vulnerability of Smallholder Agriculture to Climate Variability/Change in Boset Woreda, Oromia Region, Ethiopia
    (2013-06) Bekele, Emebet; Bewket, Woldeamelak (PhD)
    This paper examined vulnerability of smallholder agriculture to climate variability/change in the Oromia region of Boset Woreda by developing vulnerability index and comparing vulnerability indicators across the three agro-ecological zones. It also assessed the perceptions of farmers to climate variability/change, undertaken adaptation measures and perceived impacts of the event on the society. The study used semi-structured interview to gather data from households, government officials and experts; and secondary data from published and unpublished sources, and systematically analyzes the data both using qualitative and quantitative analysis. The result showed that the trend of gradual and extreme weather change increased agriculture vulnerability in the study area. According to the 30 years (1981-2010) metrological data, rainfall was decreasing with a rate of 2.2 mm while temperature was rising by 0.0090c. Farmers at the area also agreed with the metrological data. 95.7%, 78.7 % and 93.1% of the respondents claimed that there had been an overall increase in temperature, flood and drought occurrence and decrease in rainfall respectively with compared to the past years. Regarding the agricultural impacts, 97.9% of the respondents stated having a considerable reduction of production while 88.8% increase in incidence of plant diseases. Similarly, 87.8%, 62%, 76.7%, and 58.6% of respondents perceived an increase in incidence of insects, animal diseases, weeds and flood and drought respectively. To cope with the impacts, on average 63 % of the farmers used one or more of adaptation mechanisms though, the coping mechanisms were not sufficient to tackle the challenges. The study also revealed that agro-ecology zone with low potential impact and high adaptive capacity had the lowest vulnerability level than with high potential impacts and low adaptive capacity. Accordingly, the warm moist lowlands agro-ecology zone had the lowest agriculture vulnerability level due to its low potential impact and high adaptive capacity followed by Sub moist mid highlands. In contrast, because of its combined high sensitivity and exposure and low adaptive capacity the warm Sub- Moist lowlands agro-ecology zone had the highest level of agriculture vulnerability. Thus, as climate variability/change is an unavoidable phenomenon, reducing the sensitivity of the farmers and the ecosystem and increasing the adaptive capacity of the farmers is very crucial so as to minimize the vulnerability of agriculture to climate variability/change