LINGUIST List 15.2531

Sat Sep 11 2004

Jobs: English/Text/Corpus Ling: Post Doc, CEA France

Editor for this issue: Vanessa Manion <vanessalinguistlist.org>

Directory

  • Gregory.Grefenstette, Jobs: English & Text/corpus Linguistics: Post Doc, CEA France, France

    Message 1: Jobs: English & Text/corpus Linguistics: Post Doc, CEA France, France

     Date: Wed, 8 Sep 2004 10:51:31 -0400 (EDT)
    From: Gregory.Grefenstette <Gregory.Grefenstettecea.fr>
    Subject: Jobs: English & Text/corpus Linguistics: Post Doc, CEA France, France




    University or Organization: CEA France Department: LIC2M Multimedia multilingual laboratory Rank of Job: Post Doc Specialty Areas: Text/Corpus Linguistics Required Language(s): English (Code = ENG)

    Description:

    MUSCLE Internal Fellowship Program Project: Creation of a large-scale image ontology.

    Name of the hosting institutes

    17-CEA, Fontenay-aux-Roses, France Scientist to host the fellow: Grefenstettegcea.fr E-mail: Phone number: 33-146549656

    05-BILKENT, Turkey Scientist to host the fellow: E-mail: duygulucs.bilkent.edu.tr Phone number: 90 - 312 - 290 31 43 Description:

    An unresolved, general problem is recognizing objects in images. We propose exploiting written language resources and web-based image mining for building a large-scale visual dictionary.

    The project involves using text analysis and lexical resources to identify objects that might be found in a picture, and then constituting a large visual dictionary of those objects by trawling image repositories on the Web. This post-doc would be expected to produce a system that would construct an image ontology for tens of thousands of objects and comprising millions of images.

    This post doc addresses itself to a researcher having experience in both text processing and image processing. Text processing here involves creating an ontology of objects that can appear in a picture. Research involved in linguistics concerns producing an automated method for identifying from a large text corpus which terms refer to something that can appear in an image.

    For example, from lexical resources or text mining, the post-doc's system might identify that an ''English Toy Spaniel'' is a type of dog. This fact would be automatically included in the ontology and then the system built by the researcher would automatically gather images of that animal. In a further step, these images would be used to create a signature for the image of an ''English Toy Spaniel.'' In such a way, a very large image ontology would be created.

    Research involves identifying portrayable objects in text, and extracting image signatures for each collection of objects. Such a project ideally requires a post-doc who has experience both with image processing and text mining. The benefits for multimedia understanding are vast, since we currently have no list of what objects can be found in an image, and no large representative sets of images for all these objects. Description of the proposed joint programme of activities

    The post-doc will spend the first nine-months at the CEA in France, studying the problem of building a large-scale image ontology. The definition of the ontology contents, and development of tools for mining the images for the ontology for the web would be completed at the CEA. As much of the ontology as possible would be instantiated at the CEA. Initial exploration of creating object signatures would be begun using the CEA image indexing tools.

    The next nine-months would take this partially instantiated ontology to Bilkent where complete signatures would be built for all objects the ontology and experimentaton on object recognition using this ontology would be performed.

    Remuneration: The Fellow will receive a fixed stipend per month. Each and every Fellow, regardless of the location of the hosting institute, will receive 29 660 Euro net per year, or approximately 2 470 Euro net per month. For insurance questions see, http://www.muscle-noe.org/ifp.html

    - 1st October 2004 Closing date for candidates to apply; Negotiation between the receiving institutes and the selected Fellows begins: - 1st November 2004 End of negotiation period - 1st March 2005 at latest Fellowship periods begin

    Address for Applications:

    Attn: Dr. Gregory Grefenstette Commissariat a l Energie Atomique B.P. 6 18 route du Panorama Fontenay-aux-Roses, 92265 France Applications are due by 01-Oct-2004

    Contact Information:

    Dr. Gregory Grefenstette Email: Gregory.Grefenstettecea.fr Tel: +33 1 46 54 96 56 Fax: +33 1 46 54 91 15 Website: http://www.muscle-noe.org/jobs.html

    This announcement was accompanied by a donation to the LINGUIST List!