<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-04564690</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-20T02:53:45+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">On the Use of Statistical Machine Translation for Suggesting Variable Names for Decompiled Code: The Pharo Case</title>
            <author role="aut">
              <persName>
                <forename type="first">Juan</forename>
                <forename type="middle">Pablo</forename>
                <surname>Sandoval Alcocer</surname>
              </persName>
              <idno type="halauthorid">3142624-0</idno>
              <affiliation ref="#struct-252664"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Harold</forename>
                <surname>Camacho-Jaimes</surname>
              </persName>
              <idno type="halauthorid">3142625-0</idno>
              <affiliation ref="#struct-1182881"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Geraldine</forename>
                <surname>Galindo-Gutierrez</surname>
              </persName>
              <idno type="halauthorid">2989665-0</idno>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Andrés</forename>
                <surname>Neyem</surname>
              </persName>
              <idno type="halauthorid">2054684-0</idno>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Alexandre</forename>
                <surname>Bergel</surname>
              </persName>
              <idno type="halauthorid">264870-0</idno>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Stéphane</forename>
                <surname>Ducasse</surname>
              </persName>
              <email type="md5">5da97c2837b65f20186e33a01b85efad</email>
              <email type="domain">inria.fr</email>
              <ptr type="url" target="http://stephane.ducasse.free.fr"/>
              <idno type="idhal" notation="string">stephane-ducasse</idno>
              <idno type="idhal" notation="numeric">939</idno>
              <idno type="halauthorid" notation="string">17081-939</idno>
              <idno type="IDREF">https://www.idref.fr/034814884</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-6070-6599</idno>
              <idno type="ARXIV">https://arxiv.org/a/ducasse_s_1</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=7fHNqtoAAAAJ</idno>
              <affiliation ref="#struct-1166973"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Lse</forename>
                <surname>Lse</surname>
              </persName>
              <email type="md5">5da97c2837b65f20186e33a01b85efad</email>
              <email type="domain">inria.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2024-04-30 17:46:36</date>
              <date type="whenModified">2025-10-28 10:40:03</date>
              <date type="whenReleased">2024-05-02 09:43:42</date>
              <date type="whenProduced">2024-04-28</date>
              <date type="whenEndEmbargoed">2024-04-30</date>
              <ref type="file" target="https://inria.hal.science/hal-04564690v1/document">
                <date notBefore="2024-04-30"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://inria.hal.science/hal-04564690v1/file/Sando24a-COLA_SMT_2023_Preprint.pdf" id="file-4564690-3958836">
                <date notBefore="2024-04-30"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="152987">
                <persName>
                  <forename>Lse</forename>
                  <surname>Lse</surname>
                </persName>
                <email type="md5">5da97c2837b65f20186e33a01b85efad</email>
                <email type="domain">inria.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04564690</idno>
            <idno type="halUri">https://inria.hal.science/hal-04564690</idno>
            <idno type="halBibtex">sandovalalcocer:hal-04564690</idno>
            <idno type="halRefHtml">&lt;i&gt;Journal of Computer Languages&lt;/i&gt;, 2024</idno>
            <idno type="halRef">Journal of Computer Languages, 2024</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-4564690-3958836"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="INRIA">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="INRIA-LILLE">INRIA Lille - Nord Europe</idno>
            <idno type="stamp" n="INRIA_TEST">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="INRIA-CHILE">INRIA Chile</idno>
            <idno type="stamp" n="CRISTAL">Centre de Recherche en Informatique, Signal et Automatique de Lille (CRISTAL)</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="PHARO">Pharo</idno>
            <idno type="stamp" n="UNIV-LILLE">Université de Lille</idno>
            <idno type="stamp" n="CRISTAL-EVREF" corresp="CRISTAL">EVREF</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">On the Use of Statistical Machine Translation for Suggesting Variable Names for Decompiled Code: The Pharo Case</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Juan</forename>
                    <forename type="middle">Pablo</forename>
                    <surname>Sandoval Alcocer</surname>
                  </persName>
                  <idno type="halauthorid">3142624-0</idno>
                  <affiliation ref="#struct-252664"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Harold</forename>
                    <surname>Camacho-Jaimes</surname>
                  </persName>
                  <idno type="halauthorid">3142625-0</idno>
                  <affiliation ref="#struct-1182881"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Geraldine</forename>
                    <surname>Galindo-Gutierrez</surname>
                  </persName>
                  <idno type="halauthorid">2989665-0</idno>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Andrés</forename>
                    <surname>Neyem</surname>
                  </persName>
                  <idno type="halauthorid">2054684-0</idno>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Alexandre</forename>
                    <surname>Bergel</surname>
                  </persName>
                  <idno type="halauthorid">264870-0</idno>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Stéphane</forename>
                    <surname>Ducasse</surname>
                  </persName>
                  <email type="md5">5da97c2837b65f20186e33a01b85efad</email>
                  <email type="domain">inria.fr</email>
                  <ptr type="url" target="http://stephane.ducasse.free.fr"/>
                  <idno type="idhal" notation="string">stephane-ducasse</idno>
                  <idno type="idhal" notation="numeric">939</idno>
                  <idno type="halauthorid" notation="string">17081-939</idno>
                  <idno type="IDREF">https://www.idref.fr/034814884</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-6070-6599</idno>
                  <idno type="ARXIV">https://arxiv.org/a/ducasse_s_1</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=7fHNqtoAAAAJ</idno>
                  <affiliation ref="#struct-1166973"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">149635</idno>
                <idno type="issn">2590-1184</idno>
                <title level="j">Journal of Computer Languages</title>
                <imprint>
                  <publisher>Elsevier</publisher>
                  <date type="datePub">2024-04-28</date>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info.info-se">Computer Science [cs]/Software Engineering [cs.SE]</classCode>
              <classCode scheme="halTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halOldTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halTreeTypology" n="ART">Journal articles</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Adequately selecting variable names is a difficult activity for practitioners. In 2018, Jaffe et al. proposed the use of statistical machine translation (SMT) to suggest descriptive variable names for decompiled code. A large corpus of decompiled C code was used to train the SMT model. Our paper presents the results of a partial replication of Jaffe’s experiment. We apply the same technique and methodology to a dataset made of code written in the Pharo programming language. We selected Pharo since its syntax is simple - it fits on half of a postcard - and because the optimizations performed by the compiler are limited to method scope. Our results indicate that SMT may recover between 8.9% and 69.88% of the variable names depending on the training set. Our replication concludes that: (i) the accuracy depends on the code similarity between the training and testing sets; (ii) the simplicity of the Pharo syntax and the satisfactory decompiled code alignment have a positive impact on predicting variable names; and (iii) a relatively small code corpus is sufficient to train the SMT model, which shows the applicability of the approach to less popular programming languages. Additionally, to assess SMT’s potential in improving original variable names, ten Pharo developers reviewed 400 SMT name suggestions, with four reviews per variable. Only 15 suggestions (3.75%) were unanimously viewed as improvements, while 45 (11.25%) were perceived as improvements by at least two reviewers, highlighting SMT’s limitations in providing suitable alternatives.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-252664" status="VALID">
          <idno type="IdRef">029268001</idno>
          <idno type="ISNI">0000000121570406</idno>
          <idno type="ROR">https://ror.org/04teye511</idno>
          <orgName>Pontificia Universidad Católica de Chile = Pontifical Catholic University of Chile [Santiago]</orgName>
          <orgName type="acronym">PUC</orgName>
          <date type="start">1888-06-21</date>
          <desc>
            <address>
              <addrLine>Av Libertador Bernardo O'Higgins 340, Santiago, Región Metropolitana, Chili</addrLine>
              <country key="CL"/>
            </address>
            <ref type="url">http://www.uc.cl/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-1182881" status="INCOMING">
          <orgName>Universidad Católica Boliviana</orgName>
          <orgName type="acronym">UCB</orgName>
          <desc>
            <address>
              <country key="BO"/>
            </address>
          </desc>
        </org>
        <org type="researchteam" xml:id="struct-1166973" status="VALID">
          <idno type="RNSR">202324397Y</idno>
          <idno type="ROR">https://ror.org/00zm0ea22</idno>
          <orgName>Reflective Evolution of Ever-running Software Systems</orgName>
          <orgName type="acronym">EVREF</orgName>
          <date type="start">2023-04-01</date>
          <date type="end">2027-03-31</date>
          <desc>
            <address>
              <addrLine>Centre Inria de l'Université de Lille</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-104752" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-374570" type="direct"/>
            <relation active="#struct-407890" type="direct"/>
            <relation active="#struct-410272" type="direct"/>
            <relation name="UMR9189" active="#struct-120930" type="indirect"/>
            <relation name="UMR9189" active="#struct-374570" type="direct"/>
            <relation name="UMR9189" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-104752" status="VALID">
          <idno type="RNSR">200818245B</idno>
          <idno type="ROR">https://ror.org/04eej9726</idno>
          <orgName>Centre Inria de l'Université de Lille</orgName>
          <desc>
            <address>
              <addrLine>Parc Scientifique de la Haute Borne 40, avenue Halley Bât.A, Park Plaza 59650 Villeneuve d'Ascq</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/lille/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300009" status="VALID">
          <idno type="ROR">https://ror.org/02kvxyf05</idno>
          <orgName>Institut National de Recherche en Informatique et en Automatique</orgName>
          <orgName type="acronym">Inria</orgName>
          <desc>
            <address>
              <addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/en/</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-374570" status="VALID">
          <idno type="IdRef">223446556</idno>
          <idno type="ISNI">0000 0001 2242 6780</idno>
          <idno type="ROR">https://ror.org/02kzqn938</idno>
          <idno type="Wikidata">Q3551621</idno>
          <orgName>Université de Lille</orgName>
          <desc>
            <address>
              <addrLine>EPE Université de Lille. -- 42 rue Paul Duez, 59000 Lille</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-lille.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-407890" status="VALID">
          <orgName>Berger-Levrault</orgName>
          <desc>
            <address>
              <addrLine>104 avenue du Président Kennedy 75016 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.berger-levrault.com/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-410272" status="VALID">
          <idno type="IdRef">18388695X</idno>
          <idno type="RNSR">201521249L</idno>
          <idno type="ROR">https://ror.org/05vrs3189</idno>
          <idno type="Wikidata">Q116959497</idno>
          <orgName>Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189</orgName>
          <orgName type="acronym">CRIStAL</orgName>
          <date type="start">2015-01-01</date>
          <desc>
            <address>
              <addrLine>Université de Lille - Campus scientifique - Bâtiment ESPRIT - Avenue Henri Poincaré - 59655 Villeneuve d’Ascq</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cristal.univ-lille.fr/</ref>
          </desc>
          <listRelation>
            <relation name="UMR9189" active="#struct-120930" type="direct"/>
            <relation name="UMR9189" active="#struct-374570" type="direct"/>
            <relation name="UMR9189" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-120930" status="VALID">
          <idno type="IdRef">256304629</idno>
          <idno type="ISNI">0000000122034461</idno>
          <idno type="ROR">https://ror.org/01x441g73</idno>
          <orgName>Centrale Lille</orgName>
          <desc>
            <address>
              <addrLine>École Centrale de Lille - Cité Scientifique - CS 20048 59651 Villeneuve d'Ascq Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://centralelille.fr/</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-441569" status="VALID">
          <idno type="IdRef">02636817X</idno>
          <idno type="ISNI">0000000122597504</idno>
          <idno type="ROR">https://ror.org/02feahw73</idno>
          <orgName>Centre National de la Recherche Scientifique</orgName>
          <orgName type="acronym">CNRS</orgName>
          <date type="start">1939-10-19</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cnrs.fr/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>