<?xml version="1.0" encoding="UTF-8"?>
<record
    xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
    xsi:schemaLocation="http://www.loc.gov/MARC21/slim http://www.loc.gov/standards/marcxml/schema/MARC21slim.xsd"
    xmlns="http://www.loc.gov/MARC21/slim">

  <leader>03061nam a2200433   4500</leader>
  <controlfield tag="005">20260818084448.0</controlfield>
  <controlfield tag="008">080998         th                  eng  </controlfield>
  <datafield tag="035" ind1=" " ind2=" ">
    <subfield code="a">.b1149430x</subfield>
  </datafield>
  <datafield tag="099" ind1=" " ind2="9">
    <subfield code="a">AIT Thesis no. CS-95-05</subfield>
  </datafield>
  <datafield tag="100" ind1="0" ind2=" ">
    <subfield code="a">Do Duc Hanh</subfield>
  </datafield>
  <datafield tag="245" ind1="1" ind2="0">
    <subfield code="a">Compression of large Vietnamese text documents</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="a">Bangkok :</subfield>
    <subfield code="b">Asian Institute of Technology,</subfield>
    <subfield code="c">1995</subfield>
  </datafield>
  <datafield tag="300" ind1=" " ind2=" ">
    <subfield code="a">67 leaves +</subfield>
    <subfield code="e">1 online resource</subfield>
  </datafield>
  <datafield tag="490" ind1="1" ind2=" ">
    <subfield code="a">Thesis ;</subfield>
    <subfield code="v">no. CS-95-5</subfield>
  </datafield>
  <datafield tag="500" ind1=" " ind2=" ">
    <subfield code="a">A thesis submitted in the partial fulfillment of the requirement for the degree of Master of Engineering</subfield>
  </datafield>
  <datafield tag="502" ind1=" " ind2=" ">
    <subfield code="a">Thesis (M.Eng.) - Asian Institute of Technology, 1995</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">Digital libraries require efficient methods of storing vast amounts of information in such a way that provides fast search and retrieval. But there is a conflict. Decompression increases access time and the need for an index enlarges stored space. This study was involved in efficient compression methods of large Vietnamese text documents to create databases for digital libraries. The characteristics of Vietnamese text were analyzed. The zero-order word-based method coupled with the canonical Huffman coding was used to compress Vietnamese text documents. Then an in-place merging algorithm was used to create inverted files. Finally, the coding methods of integers were used to reduce a space requirement of temporary and inverted files. By the proposed approach, the documents can be decoded fast and full-text queries are supported on compressed documents. The size of compressed database (including indexing to every word) is about 40% of the original text size.</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="0">
    <subfield code="a">Data compression (Computer science)</subfield>
  </datafield>
  <datafield tag="700" ind1="1" ind2=" ">
    <subfield code="a">Huynh, Ngoc Phien,</subfield>
    <subfield code="e">Chairperson</subfield>
  </datafield>
  <datafield tag="700" ind1="1" ind2=" ">
    <subfield code="a">Phan, Minh Dung,</subfield>
    <subfield code="e">Examination Committee</subfield>
  </datafield>
  <datafield tag="700" ind1="1" ind2=" ">
    <subfield code="a">Batanov, Dentcho N.,</subfield>
    <subfield code="e">Examination Committee</subfield>
  </datafield>
  <datafield tag="710" ind1="2" ind2=" ">
    <subfield code="a">The Swedish International Development Authority Agency (SIDA),</subfield>
    <subfield code="e">Scholarship donor</subfield>
  </datafield>
  <datafield tag="810" ind1="2" ind2=" ">
    <subfield code="a">Asian Institute of Technology.</subfield>
    <subfield code="t">Thesis ;</subfield>
    <subfield code="v">no. CS-95-5</subfield>
  </datafield>
  <datafield tag="856" ind1=" " ind2=" ">
    <subfield code="3">Full-Text</subfield>
    <subfield code="u">http://203.159.5.9/ait-thesis/detail.php?q=B14988</subfield>
  </datafield>
  <datafield tag="907" ind1=" " ind2=" ">
    <subfield code="a">.b1149430x</subfield>
    <subfield code="b">mnait</subfield>
    <subfield code="c">v</subfield>
  </datafield>
  <datafield tag="902" ind1=" " ind2=" ">
    <subfield code="a">250325</subfield>
  </datafield>
  <datafield tag="998" ind1=" " ind2=" ">
    <subfield code="b">0</subfield>
    <subfield code="c">960624</subfield>
    <subfield code="d">m</subfield>
    <subfield code="e">a  </subfield>
    <subfield code="f">v</subfield>
    <subfield code="g">0</subfield>
  </datafield>
  <datafield tag="945" ind1=" " ind2=" ">
    <subfield code="l">mnait</subfield>
  </datafield>
  <datafield tag="945" ind1=" " ind2=" ">
    <subfield code="l">mnait</subfield>
  </datafield>
  <datafield tag="945" ind1=" " ind2=" ">
    <subfield code="l">mnarc</subfield>
  </datafield>
  <datafield tag="945" ind1=" " ind2=" ">
    <subfield code="l">mnarc</subfield>
  </datafield>
  <datafield tag="942" ind1=" " ind2=" ">
    <subfield code="c">20</subfield>
  </datafield>
  <datafield tag="942" ind1=" " ind2=" ">
    <subfield code="c">40</subfield>
  </datafield>
  <datafield tag="909" ind1=" " ind2=" ">
    <subfield code="a">Barcode : 30050120675797</subfield>
    <subfield code="b">CREATED : 1996-05-21</subfield>
    <subfield code="c">RECORD # : i11757619</subfield>
    <subfield code="d">LPATRON : 0</subfield>
    <subfield code="e">LCHKIN : -</subfield>
    <subfield code="f"># RENEWALS : 0</subfield>
    <subfield code="g"># OVERDUE : 0</subfield>
    <subfield code="h">IUSE3 : 0</subfield>
    <subfield code="i">TOT CHKOUT : 0</subfield>
    <subfield code="j">TOT RENEW : 0</subfield>
  </datafield>
  <datafield tag="909" ind1=" " ind2=" ">
    <subfield code="a">Barcode : 30050120676241</subfield>
    <subfield code="b">CREATED : 1996-05-21</subfield>
    <subfield code="c">RECORD # : i11757620</subfield>
    <subfield code="d">LPATRON : 0</subfield>
    <subfield code="e">LCHKIN : -</subfield>
    <subfield code="f"># RENEWALS : 0</subfield>
    <subfield code="g"># OVERDUE : 0</subfield>
    <subfield code="h">IUSE3 : 0</subfield>
    <subfield code="i">TOT CHKOUT : 1</subfield>
    <subfield code="j">TOT RENEW : 0</subfield>
  </datafield>
  <datafield tag="909" ind1=" " ind2=" ">
    <subfield code="a">Barcode : 30050120356364</subfield>
    <subfield code="b">CREATED : 2016-06-14</subfield>
    <subfield code="c">RECORD # : i1303568x</subfield>
    <subfield code="d">LPATRON : 0</subfield>
    <subfield code="e">LCHKIN : -</subfield>
    <subfield code="f"># RENEWALS : 0</subfield>
    <subfield code="g"># OVERDUE : 0</subfield>
    <subfield code="h">IUSE3 : 0</subfield>
    <subfield code="i">TOT CHKOUT : 0</subfield>
    <subfield code="j">TOT RENEW : 0</subfield>
  </datafield>
  <datafield tag="909" ind1=" " ind2=" ">
    <subfield code="a">Barcode : 30050120914980</subfield>
    <subfield code="b">CREATED : 2019-11-21</subfield>
    <subfield code="c">RECORD # : i13231674</subfield>
    <subfield code="d">LPATRON : 0</subfield>
    <subfield code="e">LCHKIN : -</subfield>
    <subfield code="f"># RENEWALS : 0</subfield>
    <subfield code="g"># OVERDUE : 0</subfield>
    <subfield code="h">IUSE3 : 0</subfield>
    <subfield code="i">TOT CHKOUT : 0</subfield>
    <subfield code="j">TOT RENEW : 0</subfield>
  </datafield>
  <datafield tag="999" ind1=" " ind2=" ">
    <subfield code="c">20563</subfield>
    <subfield code="d">20563</subfield>
  </datafield>
  <datafield tag="952" ind1=" " ind2=" ">
    <subfield code="0">0</subfield>
    <subfield code="1">0</subfield>
    <subfield code="4">0</subfield>
    <subfield code="7">0</subfield>
    <subfield code="a">MAIN</subfield>
    <subfield code="b">MAIN</subfield>
    <subfield code="c">mnait</subfield>
    <subfield code="d">2026-08-18</subfield>
    <subfield code="g">30.00</subfield>
    <subfield code="l">0</subfield>
    <subfield code="o">AIT Thesis no. CS-95-05</subfield>
    <subfield code="p">30050120675797</subfield>
    <subfield code="r">2026-08-18 08:44:48</subfield>
    <subfield code="t">1</subfield>
    <subfield code="w">2026-08-18</subfield>
    <subfield code="y">20</subfield>
  </datafield>
  <datafield tag="952" ind1=" " ind2=" ">
    <subfield code="0">0</subfield>
    <subfield code="1">0</subfield>
    <subfield code="4">0</subfield>
    <subfield code="7">0</subfield>
    <subfield code="a">MAIN</subfield>
    <subfield code="b">MAIN</subfield>
    <subfield code="c">mnait</subfield>
    <subfield code="d">2026-08-18</subfield>
    <subfield code="g">30.00</subfield>
    <subfield code="l">0</subfield>
    <subfield code="o">AIT Thesis no. CS-95-05</subfield>
    <subfield code="p">30050120676241</subfield>
    <subfield code="r">2026-08-18 08:44:48</subfield>
    <subfield code="t">2</subfield>
    <subfield code="w">2026-08-18</subfield>
    <subfield code="y">20</subfield>
  </datafield>
  <datafield tag="952" ind1=" " ind2=" ">
    <subfield code="0">0</subfield>
    <subfield code="1">0</subfield>
    <subfield code="4">0</subfield>
    <subfield code="7">0</subfield>
    <subfield code="a">MAIN</subfield>
    <subfield code="b">MAIN</subfield>
    <subfield code="c">mnarc</subfield>
    <subfield code="d">2026-08-18</subfield>
    <subfield code="l">0</subfield>
    <subfield code="o">AIT Thesis no. CS-95-05</subfield>
    <subfield code="p">30050120356364</subfield>
    <subfield code="r">2026-08-18 08:44:48</subfield>
    <subfield code="w">2026-08-18</subfield>
    <subfield code="y">40</subfield>
  </datafield>
  <datafield tag="952" ind1=" " ind2=" ">
    <subfield code="0">0</subfield>
    <subfield code="1">0</subfield>
    <subfield code="4">0</subfield>
    <subfield code="7">0</subfield>
    <subfield code="a">MAIN</subfield>
    <subfield code="b">MAIN</subfield>
    <subfield code="c">mnarc</subfield>
    <subfield code="d">2026-08-18</subfield>
    <subfield code="g">50.00</subfield>
    <subfield code="l">0</subfield>
    <subfield code="o">AIT Thesis no. CS-95-05</subfield>
    <subfield code="p">30050120914980</subfield>
    <subfield code="r">2026-08-18 08:44:48</subfield>
    <subfield code="t">3</subfield>
    <subfield code="w">2026-08-18</subfield>
    <subfield code="y">20</subfield>
  </datafield>
</record>
