This shows you the differences between two versions of the page.
Next revision | Previous revision | ||
job-2016-ligm-alpage-phd-fr [2016/04/05 15:07] matthieu.constant created |
job-2016-ligm-alpage-phd-fr [2016/06/14 21:41] (current) matthieu.constant |
||
---|---|---|---|
Line 1: | Line 1: | ||
- | L'Université Paris-Est Marne-la-Vallée | + | L'ATILF recrute un doctorant en traitement |
===== Intégrer les expressions polylexicales au coeur de l’analyse syntaxique et sémantique statistique ===== | ===== Intégrer les expressions polylexicales au coeur de l’analyse syntaxique et sémantique statistique ===== | ||
- | * **Date limite de candidature: | + | * **Candidatures acceptées jusqu' |
* **Domaine: | * **Domaine: | ||
- | * **Lieu:** [[http://ligm.u-pem.fr/ | Laboratoire d' | + | * **Lieu:** [[http://www.atilf.fr|ATILF]], Université |
- | * **Encadrant**: | + | * **Encadrant**: |
* **Co-encadrant**: | * **Co-encadrant**: | ||
* **Durée:** 3 ans, octobre 2016 à septembre 2019 | * **Durée:** 3 ans, octobre 2016 à septembre 2019 | ||
* **Rémunération: | * **Rémunération: | ||
- | * **Financement: | + | * **Financement: |
* **Mots-clés**: | * **Mots-clés**: | ||
Line 17: | Line 17: | ||
==== Contexte ==== | ==== Contexte ==== | ||
- | The proposed PhD thesis falls into the field of natural language processing at the crossroads of computer science and linguistics. In particular, it will focus on processing of multiword | + | Le sujet de thèse proposé ci-dessous se situe dans le domaine du traitement automatique des langues à la croisée des chemins entre informatique et linguistique. Il s’intéresse plus particulièrement au traitement des expressions |
- | This PhD proposal holds in the framework of the ANR-funded | + | |
----------------- | ----------------- | ||
- | ==== Profile | + | ==== Profil |
- | * Master | + | * Master |
- | * Good knowledge of French and English, another language would be a plus | + | * Bonne connaissance du Français et de l' |
- | * Interests in linguistics and familiarity with language technology | + | * Intérêt pour la linguistique et compétence en technologie des langues |
- | * Capacity to work independently and as part of a team | + | * Capacité à travailler indépendamment et en équipe |
--------------------- | --------------------- | ||
- | ==== Application | + | ==== Candidature |
- | Candidates should send the following documents in PDF format, in French or in English, to Mathieu Constant (FirstName.LastName@u-pem.fr) | + | Les candidats devront envoyer les pièces suivantes en français ou en anglais, au format |
* CV | * CV | ||
- | * Cover letter | + | * Lettre de motivation |
- | * Transcript of MSc and BSc grades (translated if not in French or English) | + | * Bulletin de notes de la Licence et du Master |
- | * Reference letters would be a plus | + | * Lettre de recommandation (serait un plus) |
------------------------------ | ------------------------------ | ||
- | ==== Hosting | + | ==== Institutions |
- | === Main affiliation | + | === Affiliation principale |
- | * **Laboratory**: [[http://ligm.u-pem.fr/ | Laboratoire d' | + | * **Laboratoire**: [[http://www.atilf.fr/ | ATILF]] |
- | * **University**: [[http:// | + | * **Université**: [[http:// |
- | === Secondary affiliation | + | === Affiliation secondaire |
- | * **Laboratory**: [[https:// | + | * **Laboratoire**: [[https:// |
- | * **Institutions**: | + | * **Institutions**: |
------------------------------- | ------------------------------- | ||
- | ==== Scientific description | + | ==== Description scientifique |
+ | |||
+ | Cette thèse consiste à revisiter l’analyse syntaxique et sémantique statistique à l’aune des expressions polylexicales. Plus précisément, | ||
- | This PhD thesis aims at revisiting statistical syntactic and semantic analysis in the light of multiword | + | La prise en compte des expressions |
- | Taking multiword expressions into account is a challenge for automatic text analysis, mainly due to their non-compositionality, | + | Le ou les analyseurs développés tenteront de combiner deux caractéristiques souvent antagoniques: |
- | Given this new representation, the next step will consist in developing new parsing algorithms integrating MWEs. | + | |
- | Priority will be given to a system that jointly performs both MWE identification and syntactic parsing, in such a way both tasks can mutually inform each other. Multiword expressions generally representing semantic units, a natural extension of this joint system is to develop a system that automatically constructs | + | |
- | The developed parsers should combine two features: speed and accuracy. To reach high accuracy, joint prediction can enable the system to benefit from richer linguistic information at analysis time. Further, the use of deep learning techniques and large-scale MWE resources can be investigated. Yet this sophistication comes at the cost of increased complexity and ambiguity. A possible solution is to add constraints reducing search space. Finally, we wish the proposed solutions to have (quasi-)linear speed complexity, in order to reasonably consider parsing big textual data. | + | Cette thèse s' |
- | This thesis will be in collaboration with Joakim Nivre (Univ. Uppsala, Sweden), in the framework of the European COST Action PARSEME. | ||
------------------------- | ------------------------- | ||
- | ==== Bibliography | + | ==== Bibliographie |