<?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>03149nas a2200445 a 4500</leader>
  <controlfield tag="005">20260818134219.0</controlfield>
  <controlfield tag="008">200707s2017    th uu m rtt   0|  a1eng d</controlfield>
  <datafield tag="035" ind1=" " ind2=" ">
    <subfield code="a">.b1234610x</subfield>
  </datafield>
  <datafield tag="099" ind1=" " ind2="9">
    <subfield code="a">AIT RSPR no.IM-17-12  </subfield>
  </datafield>
  <datafield tag="100" ind1="1" ind2=" ">
    <subfield code="a">Akhileshwar, Chennu  </subfield>
  </datafield>
  <datafield tag="245" ind1="1" ind2="0">
    <subfield code="a">Identifying deplicate questions on Quora</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="a">Pathum Thani, Thailand :</subfield>
    <subfield code="b">Asian Institute of Technology,</subfield>
    <subfield code="c">2017</subfield>
  </datafield>
  <datafield tag="300" ind1=" " ind2=" ">
    <subfield code="a">40 leaves :</subfield>
    <subfield code="b">ill.</subfield>
  </datafield>
  <datafield tag="490" ind1="1" ind2=" ">
    <subfield code="a">Research studies project report  ;</subfield>
    <subfield code="v">no. IM-17-12</subfield>
  </datafield>
  <datafield tag="500" ind1=" " ind2=" ">
    <subfield code="a">A research submitted in partial fulfillment of the requirements for the  degree of Master of Engineering in Information Management, School of Engineering and Technology</subfield>
  </datafield>
  <datafield tag="502" ind1=" " ind2=" ">
    <subfield code="a">Research studies project report (M. Eng.) - Asian Institute of Technology, 2017</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">Finding whether the two questions are asking the same thing can be challenging, as word choice and sentence structure may vary signi{uFB01}cantly. Some of the natural language processing techniques have been found to have the limited success in separating related question from duplicate ones. Quora is a very good source which helps the users to exchange their knowledge and they also face this problem of duplicate questions. Since Quora gives importance to similar questions problem, it want to provide a good experience for both the question seeker and writer. Using a data set question pairs provided by Quora in Kaggle, we extract the features from the data set by using some methods like common word share, Jaccard Similarity Coefcient, Cosine Similarity, Tf-Idf. After extracting the features from the data we use some machine learning algorithms to build a model using training data. By using this model we get the {uFB01}nal values of the test data set. </subfield>
  </datafield>
  <datafield tag="650" ind1=" " ind2="0">
    <subfield code="a">Machine learning</subfield>
    <subfield code="x">Technique</subfield>
  </datafield>
  <datafield tag="700" ind1="1" ind2=" ">
    <subfield code="a">Sumanta, Guha,</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">Bohez, Erik L.J.,</subfield>
    <subfield code="e">Examination Committee</subfield>
  </datafield>
  <datafield tag="710" ind1="2" ind2=" ">
    <subfield code="a">AIT Fellowship,</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">Research studies project report  ;</subfield>
    <subfield code="v">no. IM-17-12</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=B06933</subfield>
  </datafield>
  <datafield tag="907" ind1=" " ind2=" ">
    <subfield code="a">.b1234610x</subfield>
    <subfield code="b">mnait</subfield>
    <subfield code="c">m</subfield>
  </datafield>
  <datafield tag="902" ind1=" " ind2=" ">
    <subfield code="a">240419</subfield>
  </datafield>
  <datafield tag="998" ind1=" " ind2=" ">
    <subfield code="b">0</subfield>
    <subfield code="c">200707</subfield>
    <subfield code="d">m</subfield>
    <subfield code="e">a  </subfield>
    <subfield code="f">m</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">40</subfield>
  </datafield>
  <datafield tag="942" ind1=" " ind2=" ">
    <subfield code="c">61</subfield>
  </datafield>
  <datafield tag="942" ind1=" " ind2=" ">
    <subfield code="c">20</subfield>
  </datafield>
  <datafield tag="909" ind1=" " ind2=" ">
    <subfield code="a">Barcode : 30050120890826</subfield>
    <subfield code="b">CREATED : 2020-06-22</subfield>
    <subfield code="c">RECORD # : i13277315</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 : -</subfield>
    <subfield code="b">CREATED : 2020-06-22</subfield>
    <subfield code="c">RECORD # : i13277327</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 : 30050120982649</subfield>
    <subfield code="b">CREATED : 2020-07-14</subfield>
    <subfield code="c">RECORD # : i13282256</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 : 30050120982631</subfield>
    <subfield code="b">CREATED : 2020-07-14</subfield>
    <subfield code="c">RECORD # : i13282268</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">57554</subfield>
    <subfield code="d">57554</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 RSPR no.IM-17-12</subfield>
    <subfield code="p">30050120890826</subfield>
    <subfield code="r">2026-08-18 13:42:19</subfield>
    <subfield code="t">1</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="l">0</subfield>
    <subfield code="o">AIT RSPR no.IM-17-12</subfield>
    <subfield code="r">2026-08-18 13:42:19</subfield>
    <subfield code="w">2026-08-18</subfield>
    <subfield code="y">61</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">50.00</subfield>
    <subfield code="l">0</subfield>
    <subfield code="o">AIT RSPR no.IM-17-12</subfield>
    <subfield code="p">30050120982649</subfield>
    <subfield code="r">2026-08-18 13:42:19</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">50.00</subfield>
    <subfield code="l">0</subfield>
    <subfield code="o">AIT RSPR no.IM-17-12</subfield>
    <subfield code="p">30050120982631</subfield>
    <subfield code="r">2026-08-18 13:42:19</subfield>
    <subfield code="t">2</subfield>
    <subfield code="w">2026-08-18</subfield>
    <subfield code="y">20</subfield>
  </datafield>
</record>
