<?xml version="1.0" encoding="UTF-8"?><lom xmlns="http://ltsc.ieee.org/xsd/LOM" xmlns:lomfr="http://www.lom-fr.fr/xsd/LOMFR" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://ltsc.ieee.org/xsd/LOM http://www.lom-fr.fr/xsd/lomfrv1.0/std/lomfr.xsd">
<general>
<identifier>
<catalog>Canal-U_Ocms</catalog>
<entry>18663</entry>
</identifier>
<title><string language="fre"><![CDATA[05a - Apprentissage par imitation pour l’étiquetage de séquences : vers une formalisation des méthodes d’étiquetage easy-first (taln2015)]]></string></title>
<language>FRE</language>
<description>
<string language="fre"><![CDATA[Sessions orales TALN 2015 – Mardi 23 juin 2015
Session Extraction d’information
Apprentissage par imitation pour l’étiquetage de séquences : vers une formalisation des méthodes d’étiquetage easy-first
Elena Knyazeva, Guillaume Wisniewski et François Yvon
Résumé : Structured learning techniques, aimed at modeling structured objects such as labeled trees or strings, are computationally expensive. Many attempts have been made to reduce their complexity, either to speed up learning et inference, or to take richer dependencies into account. These attempts typically rely on approximate inference techniques and usually provide very little
theoretical guarantee regarding the optimality of the solutions they find.
In this work we study a new formulation of structured learning where inference is primarily viewed as an incremental process along which a solution is progressively computed. This framework generalizes several structured learning approaches. Building on the connections between this framework and reinforcement learning, we propose a theoretically sound method to learn to perform approximate inference. Experiments on four sequence labeling tasks show that our
approach is very competitive when compared to several strong baselines. Structured learning techniques, aimed at modeling structured objects such as labeled trees or strings, are computationally expensive. Many attempts have been made to reduce their complexity, either to speed up learning and inference, or to take richer dependencies into account. These attempts typically rely on approximate inference techniques and usually provide very little theoretical guarantee regarding the optimality of the solutions they find.]]></string></description>
<keyword><string language="fre"><![CDATA[traitement automatique du langage naturel]]></string></keyword><keyword><string language="fre"><![CDATA[taln2015]]></string></keyword>
<lomfr:documentType>
<lomfr:source>LOMFRv1.0</lomfr:source>
<lomfr:value>image en mouvement</lomfr:value>
</lomfr:documentType>
</general><lifeCycle>
<contribute>
<role>
<source>LOMv1.0</source>
<value>author</value>
</role> 
<date><dateTime>2015-06-23</dateTime></date>
</contribute>
</lifeCycle>
<metaMetadata>
<metadataSchema>LOMv1.0</metadataSchema>
<metadataSchema>LOMFRv1.0</metadataSchema>
</metaMetadata>
<technical>
<format>video/mp4</format>
<location><![CDATA[https://www.canal-u.tv/video/centre_d_enseignement_multimedia_universitaire_c_e_m_u/05a_apprentissage_par_imitation_pour_l_etiquetage_de_sequences_vers_une_formalisation_des_methodes_d_etiquetage_easy_first_taln2015.18663]]></location>
<location><![CDATA[https://streaming-canal-u.fmsh.fr/vod/media/canalu/videos/centre_d_enseignement_multimedia_universitaire_c_e_m_u_universit/04d.extraction.automatique.de.paraphrases.grand.public.pour.les.termes.m.dicaux.taln2015.copie._18663/05a_knyazeva_sd.mp4]]></location>
<location><![CDATA[https://streaming-canal-u.fmsh.fr/vod/media/canalu/videos/centre_d_enseignement_multimedia_universitaire_c_e_m_u_universit/05a.apprentissage.par.imitation.pour.la.tiquetage.de.s.quences.vers.une.formalisation.des.m.thodes.da.tiquetage.easy.first.taln2015._18663/05a_knyazeva_bd.mp4]]></location><location><![CDATA[https://streaming-canal-u.fmsh.fr/vod/media/canalu/videos/centre_d_enseignement_multimedia_universitaire_c_e_m_u_universit/04d.extraction.automatique.de.paraphrases.grand.public.pour.les.termes.m.dicaux.taln2015.copie._18663/05a_knyazeva_hd.mp4]]></location>
<size>138234866</size>
<duration><duration>PT0H27M31S</duration></duration>
</technical>
<educational>
<learningResourceType>
<source>LOMv1.0</source>
<value>lecture</value>
</learningResourceType>
<context>
<source>LOMv1.0</source>
<value>higher education</value>
</context>
</educational>
<rights>
<cost>
<source>LOMv1.0</source>
<value>no</value>
</cost>
<copyrightAndOtherRestrictions>
<source>LOMv1.0</source>
<value>no</value>
</copyrightAndOtherRestrictions>
<description>
<string language="fre"><![CDATA[Droits réservés à l'éditeur et aux auteurs. 
]]></string>
</description>
</rights>
<relation>
<kind>
<source>LOMv1.0</source>
<value>ispartof</value>
</kind>
<resource>
<identifier>
<catalog>URI</catalog>
<entry>https://www.canal-u.tv/producteurs/centre_d_enseignement_multimedia_universitaire_c_e_m_u/taln_2015/session_extraction_d_information_taln_2015</entry>
</identifier>
<description>
<string language="fre"><![CDATA[Session extraction d'information (taln 2015)]]></string>
</description>
</resource>
</relation>
<classification>
<purpose>
<source>LOMv1.0</source>
<value>discipline</value>
</purpose>
<taxonPath>
<source>
<string language="fre"><![CDATA[Universités Numériques Thématiques 2009 http://www.universites-numeriques.fr]]></string>
</source>
<taxon>
<id/>
<entry>
<string language="fre"/>
</entry>
</taxon>
</taxonPath>
</classification>
<classification>
<purpose>
<source>LOMv1.0</source>
<value>discipline</value>
</purpose>
<taxonPath>
<source>
<string language="fre">CDD 22e éd.</string>
<string language="eng">DDC 22nd ed.</string>
</source>
<taxon>
<id>418.02</id>
<entry>
<string language="fre"><![CDATA[Traduction automatique]]></string>
</entry>
</taxon>
</taxonPath>
<taxonPath>
<source>
<string language="fre">CDD 22e éd.</string>
<string language="eng">DDC 22nd ed.</string>
</source>
<taxon>
<id>410.285</id>
<entry>
<string language="fre"><![CDATA[Informatique appliquée à la linguistique]]></string>
</entry>
</taxon>
</taxonPath>
</classification> </lom>