Din jobbevakning har skapats.
CEA Tech
PhD position - Incorporating expert knowledge and linguistic resources in deep neural networks for multi-domain and multilingual adaptation
CEA Tech
CEA Tech is building on CEA Leti’s successful track record innovating for industry.
Besök arbetsgivarsida
OM TJÄNSTEN
Publicerad: 5 dagar sedan
Sista ansökningsdatum: okt 31
Plats: Grenoble, Frankrike
Du måste logga in eller skapa ett konto för att spara detta jobb
Ange gärna att du hittade det här jobbet på Academic Positions i din ansökan.
DELA DETTA JOBB

PhD position - Incorporating expert knowledge and linguistic resources in deep neural networks for multi-domain and multilingual adaptation

SL-DRT-19-0750

RESEARCH FIELD

Computer science and software

ABSTRACT

Recent deep learning architectures and algorithms have shown impressive results for several Natural Language Processing (NLP) tasks such as Named entity recognition, Part-of-Speech tagging, Dependency parsing and Semantic role labelling. The actual performance of certain NLP tools for English evaluated on in-domain data is close to human level, thanks to deep learning models trained on huge annotated datasets. Contrariwise, approaching human-level accuracy on more complex domains and low-resource languages is still a hard issue. The proposed subject aims to explore and experiment new approaches based on the integration of expert knowledge and available linguistic resources in deep neural networks in order to improve the performance of NLP tools for specialty areas and low-resource languages.We propose to tackle this issue along the following key aspects, as an extension of the research work already carried out at LVIC laboratory:- Taking into account heterogeneous expert knowledge and linguistic resources: Ontologies, Terminology databases, Lexicons, Named entity recognition rules, Dependency parsing recognition rules, etc.- Implementing a formalism to describe expert knowledge and linguistic resources in a multi-level representation. The objective is to define a structure in which the different types of expert knowledge and linguistic resources will be represented separately but the whole representation would be described in the same format (model).- Exploring new strategies for incorporating expert knowledge and linguistic resources in deep neural networks. The underlying idea is to propose an integration mechanism which can be adapted to each expert knowledge and linguistic resource.

LOCATION

Département Intelligence Ambiante et Systèmes Interactifs (LIST)

Vision & Ingénierie des Contenus (SAC)

Saclay

CONTACT PERSON

SEMMAR Nasredine

CEA

DRT/DIASI//LVIC

CEA Saclay Nano-INNOVInstitut CARNOT CEA LISTLaboratoire Vision et Ingénierie des Contenus (LVIC)Point courrier n°17391191 Gif sur Yvette CEDEX

Phone number: +33 1 69 08 01 46

Email: nasredine.semmar@cea.fr

UNIVERSITY / GRADUATE SCHOOL

Paris-Saclay

Sciences et Technologies de l'Information et de la Communication (STIC)

FIND OUT MORE

https://scholar.google.fr/citations?user=RoRd7_4AAAAJ&hl=fr

http://www.kalisteo.fr/fr/index.htm

START DATE

Start date on 01-03-2019

THESIS SUPERVISOR

ALLAUZEN Alexandre

Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur (LIMSI) - CNRS

Equipe Traitement du Langage Parlé (TLP)

LIMSI-CNRSEquipe Traitement du Langage ParléBâtiment 507Université Paris-Sud91403 Orsay

Phone number: 01 69 15 80 27

Email: alexandre.allauzen@limsi.fr

« The age limit is 26 years for PhD offers and 30 years old for post-doc offers. »

Ansök nu
Du måste logga in eller skapa ett konto för att spara detta jobb

SÖK TJÄNSTEN

Personliga uppgifter
Ladda upp CV och bilagor
Filformatet måste vara .doc, .pdf, eller .rtf, och filstorleken får inte överstiga 2 MB.
Filformatet måste vara .doc, .pdf, eller .rtf, och filstorleken får inte överstiga 2 MB.

Genom att ansöka om jobb via Academic Positions godkänner du våra användarvillkor och vår integritetspolicy.

104 JOBB FRÅN DENNA ARBETSGIVARE

CEA Tech
CEA Tech
Plats: Grenoble, Frankrike | Ansök senast okt 31
PhD position - Hardware/Software co-design of countermeasures against fault injection attacks
SL-DRT-19-0748 RESEARCH FIELD Computer science and software ABSTRACT The thesis will focus on the hardware/software co-design of countermeasures against physical attacks, in particular, fault injection attacks. We will aim at developping new securing...
CEA Tech
CEA Tech
Plats: Grenoble, Frankrike | Ansök senast okt 31
PhD position - Detection and location of faults in a multiconductor transmission line
SL-DRT-19-0758 RESEARCH FIELD Mathematics - Numerical analysis - Simulation ABSTRACT The proper functioning of a distribution network depends on the ability to quickly detect the occurrence of faults, such as discharges, short circuits or the penetration of...
CEA Tech
CEA Tech
Plats: Grenoble, Frankrike | Ansök senast okt 31
PhD position - Design, simulation, fabrication and characterization of an innovative logic/memory CUBE for In-Memory-Computing
SL-DRT-19-0747 RESEARCH FIELD Electronics and microelectronics - Optoelectronics ABSTRACT For integrated circuits to be able to leverage the future “data deluge” coming from the cloud and cyber-physical systems, the historical scaling of...
CEA Tech
CEA Tech
Plats: Grenoble, Frankrike
Post Doc - Detection of small particules in the environment with nanomechanical resonators
PsD-DRT-19-0033 RESEARCH FIELD Electronics and microelectronics - Optoelectronics ABSTRACT Today, there are solutions for detecting and quantifying PM10 and PM2.5 type particles (10 and 2.5µm diameter); their reliability depends essentially on their cost....

CAREER ADVICE

[[excerpt]]

By [[ author ]]
Posted [[ publishingDate ]]

[[title]] ([[ nbHits ]])

[[title]] ([[ nbHits ]])

[[title]] ([[ nbHits ]])

No results found for

Search tip

  • Check for spelling mistakes
  • Reduce the number of keywords used or try using a broader search phrase
[[ name ]]
[[ name ]]
[[ excerpt ]]
[[ city ]], [[ region ]] [[ availableJobsBlock ]]
Featured Featured employer
Short list
Expand list