About | Contact Us | Register | Login
ProceedingsSeriesJournalsSearchEAI
Advances of Science and Technology. 8th EAI International Conference, ICAST 2020, Bahir Dar, Ethiopia, October 2-4, 2020, Proceedings, Part I

Research Article

Amharic Information Retrieval Based on Query Expansion Using Semantic Vocabulary

Download(Requires a free EAI acccount)
2 downloads
Cite
BibTeX Plain Text
  • @INPROCEEDINGS{10.1007/978-3-030-80621-7_29,
        author={Berihun Getnet and Yaregal Assabie},
        title={Amharic Information Retrieval Based on Query Expansion Using Semantic Vocabulary},
        proceedings={Advances of Science and Technology. 8th EAI International Conference, ICAST 2020, Bahir Dar, Ethiopia, October 2-4, 2020, Proceedings, Part I},
        proceedings_a={ICAST},
        year={2021},
        month={7},
        keywords={Query expansion Semantic vocabulary Word embedding Amharic information retrieval},
        doi={10.1007/978-3-030-80621-7_29}
    }
    
  • Berihun Getnet
    Yaregal Assabie
    Year: 2021
    Amharic Information Retrieval Based on Query Expansion Using Semantic Vocabulary
    ICAST
    Springer
    DOI: 10.1007/978-3-030-80621-7_29
Berihun Getnet1,*, Yaregal Assabie1
  • 1: Department of Computer Science
*Contact email: berihun.getnet@wku.edu.et

Abstract

The increase in large scale data available from different sources has demanded advancement in information retrieval. As a result, information retrieval based on learning from high dimensional vectors based on the words adjacent to other words or surrounding terms has become more attractive in recent times. The meaning is extracted from the context of words but not using the actual sense of words. The system responds to relevant results for the users by expanding the original queries from semantic lexical resources constructed automatically from a text corpus using neural word embedding. In this study, we propose query expansion for Amharic information retrieval using semantic vocabulary. The semantic vocabulary is automatically constructed from a text corpus using neural word embedding. The user’s query is expanded based on the word analog prediction. Information retrieval using semantic vocabulary based on ranked and unranked retrieval increases by a recall of 24 and 15%, respectively albeit at the expense of some precision.

Keywords
Query expansion Semantic vocabulary Word embedding Amharic information retrieval
Published
2021-07-15
Appears in
SpringerLink
http://dx.doi.org/10.1007/978-3-030-80621-7_29
Copyright © 2020–2025 ICST
EBSCOProQuestDBLPDOAJPortico
EAI Logo

About EAI

  • Who We Are
  • Leadership
  • Research Areas
  • Partners
  • Media Center

Community

  • Membership
  • Conference
  • Recognition
  • Sponsor Us

Publish with EAI

  • Publishing
  • Journals
  • Proceedings
  • Books
  • EUDL