hal.archives-ouvertes.fr
Open in
urlscan Pro
193.48.96.10
Public Scan
URL:
https://hal.archives-ouvertes.fr/hal-03853268
Submission: On November 15 via manual from AT — Scanned from FR
Submission: On November 15 via manual from AT — Scanned from FR
Form analysis
2 forms found in the DOMPOST /user/login?url=https://hal.archives-ouvertes.fr/hal-03853268
<form class="form-inline pull-right" style="margin-top: 8px; margin-right: 8px;" action="/user/login?url=https://hal.archives-ouvertes.fr/hal-03853268" id="form-login" method="post">
<input type="hidden" name="forward-controller" value="view">
<input type="hidden" name="forward-action" value="index">
<input type="hidden" name="identifiant" value="hal-03853268">
<div class="btn-group">
<button class="btn btn-small btn-primary" type="button" onclick="$('#form-login').submit();" accesskey="l">
<span class="glyphicon glyphicon-user glyphicon-white" aria-hidden="true"></span> Connexion</button>
<button class="btn btn-small btn-primary dropdown-toggle" data-toggle="dropdown" type="button">
<span class="caret" style="border-top-color: #fff; border-bottom-color: #fff;"></span>
</button>
<ul class="dropdown-menu pull-right">
<li> <a id="cas2" href="/user/login?authType=CAS&url=https://hal.archives-ouvertes.fr/hal-03853268">Connexion</a>
</li>
<li>
<a id="getorcid2" href="/user/login?authType=ORCID&url=https://hal.archives-ouvertes.fr/hal-03853268">Connexion avec ORCID</a>
</li>
<li><a id="coidp" href="https://hal.archives-ouvertes.fr/user/login?authType=IDP&url=https://hal.archives-ouvertes.fr/hal-03853268">se connecter avec Fédération</a></li>
<li class="divider"></li>
<li><a href="/user/create">Créer un compte</a></li>
<li class="divider"></li>
<li><a href="/user/lostpassword">Mot de passe oublié ?</a></li>
<li><a href="/user/lostlogin">Login oublié ?</a></li>
</ul>
</div>
</form>
POST #
<form action="#" method="post" id="formLang" class="nav navbar-nav navbar-right navbar-lang">
<input type="hidden" name="lang" id="lang" value="">
<select aria-label="Change language" id="select-lang" name="Langues" onchange="changeLang(this)">
<option value="fr" selected=""> fr </option>
<option value="en"> en </option>
</select>
</form>
Text Content
Accéder directement au contenu Accéder directement à la navigation Nouvelle interface Toggle navigation Connexion * Connexion * Connexion avec ORCID * se connecter avec Fédération * * Créer un compte * * Mot de passe oublié ? * Login oublié ? fr en La connaissance libre et partagée * Accueil * Dépôt * Consultation * Les derniers dépôts * Par type de publication * Par discipline * Par année de publication * Par structure de recherche * Les portails de l'archive * Recherche * Documentation hal-03853268, version 1 Article dans une revue A COMPREHENSIVE REVIEW OF STACKING METHODS FOR SEMANTIC SIMILARITY MEASUREMENT Jorge Martinez-Gil 1 Détails 1 SCCH - Software Competence Center Hagenberg > Jorge Martinez-Gil 1 > Auteur > PersonId : 17728 > IdHAL : martinez-gil-jorgeORCID : 0000-0002-5730-7965IdRef : 253122732 1 SCCH - Software Competence Center Hagenberg (Softwarepark 21 A-4232 Hagenberg Austria - Autriche) StructId : 46694 * JKU - Johannes Kepler Universität Linz (Altenberger Straße 69, 4040 Linz - Autriche) StructId : 300879 Masquer les détails Abstract : This article presents a comprehensive review of stacking methods commonly used to address the challenge of automatic semantic similarity measurement in the literature. Since more than two decades of research have left various semantic similarity measures, scientists and practitioners often find many difficulties in choosing the best method to put into production. For this reason, a novel generation of strategies has been proposed to use basic semantic similarity measures using base estimators to achieve a better performance than could be gained from any of the semantic similarity measures. In this work, we analyze different stacking techniques, ranging from the classical algebraic methods to the most powerful ones based on hybridization, including blending, neural, fuzzy, and genetic-based stacking. Each technique excels in aspects such as simplicity, robustness, accuracy, interpretability, transferability, or a favorable combination of several of those aspects. The goal is that the reader can have an overview of the state-of-the-art in this field. Keywords : stacking semantic similarity semantic similarity measurement semantic similarity measures semantic textual similarity Ensemble learning semantic similarity assessment Type de document : Article dans une revue Domaine : > Informatique [cs] / Intelligence artificielle [cs.AI] Liste complète des métadonnées Voir -------------------------------------------------------------------------------- https://hal.archives-ouvertes.fr/hal-03853268 Contributeur : Martinez-Gil Jorge Connectez-vous pour contacter le contributeur Soumis le : mardi 15 novembre 2022 - 12:16:18 Dernière modification le : mardi 15 novembre 2022 - 12:16:19 IDENTIFIANTS * HAL Id : hal-03853268, version 1 * DOI : 10.1016/j.mlwa.2022.100423 CITATION Jorge Martinez-Gil. A comprehensive review of stacking methods for semantic similarity measurement. Machine Learning with Applications, 2022, 10, pp.100423. ⟨10.1016/j.mlwa.2022.100423⟩. ⟨hal-03853268⟩ EXPORTER BibTeX TEI DC DCterms EndNote Datacite PARTAGER Facebook Twitter Email Share MÉTRIQUES Consultations de la notice 0 -------------------------------------------------------------------------------- CONTACT * Support RESSOURCES * Documentation * FAQ * API * OAI-PMH * AuréHAL INFORMATION * Données personnelles * Mentions légales * Accessibilité * Conformité RGAA QUESTIONS JURIDIQUES * Je publie, quels sont mes droits ? * Sherpa Romeo PORTAILS * Liste des portails * HAL SHS * HAL Thèses * mediHAL CCSD * CCSD * episciences.org * sciencesconf.org ✓ Thanks for sharing! AddToAny More… Close Cookies management panel By allowing these third party services, you accept their cookies and the use of tracking technologies necessary for their proper functioning. Preference for all services ✓ Allow all cookies ✗ Deny all cookies * ✛ APIs APIs are used to load scripts: geolocation, search engines, translations, ... * ✛ Advertising network Ad networks can generate revenue by selling advertising space on the site. * ✛ Audience measurement The audience measurement services used to generate useful statistics attendance to improve the site. * ✛ Comments Comments managers facilitate the filing of comments and fight against spam. * ✛ Other Services to display web content. * ✛ Social networks Social networks can improve the usability of the site and help to promote it via the shares. * ✛ Support Support services allow you to get in touch with the site team and help to improve it. * ✛ Videos Video sharing services help to add rich media on the site and increase its visibility. 🍋 Cookies manager by tarteaucitron.js If you continue to browse this website, you are allowing all third-party services ✓ OK, accept all Personalize Manage services 4 Close 4 cookies hal.archives-ouvertes.fr * × _pk_id.92.c92a fe35fe7f468b319b.1668511081. * × _pk_ses.17.c92a 1 * × _pk_ses.92.c92a 1 * × _pk_id.17.c92a f3ccd97cedf5966c.1668511081.