Multiview Learning for Sequence Extraction Tasks
Subject:
With the increase of electronically available textual information in different views, new needs for Information Access systems are arising. Many new tasks lie between the classic frameworks of Information Retrieval (IR) and Information Extraction (IE). Machine Learning (ML) is playing a central role in the development of these fields but has been used for the most part for the improvement of existing models.
The thesis aims at extending the capabilities of statistical IR models to handle more complex information retrieval and extraction tasks. For this, we are interested in the use of probabilistic sequence models for sequence analysis. In particular, we will consider a text generated by two different sources where each of the texts is a sequence of symbols and not as an unordered set. From this perspective, we seek a sequence model that allows to work at a finer level than what is usually done in IR. Each model associated to a source is learned in the way to minimize the disagreement of the sequence to be extracted with the similar extracted sequence by the other model. Under this framework, we aim to deal with several text analysis tasks within a unifying formalism.
Profile:
For this position, we are looking for highly motivated people, with a passion to work in machine learning, information retrieval and the skills to develop algorithms for prediction in real-life applications. We are looking for an inquisitive mind with the curiosity to use a new and challenging technology that requires a rethinking visual processing to achieve a high payoff in terms of speed and efficiency.
We further seek a candidate with the following additional skills:
- Probability and statistics ;
- The ability to analyze, improve and propose new algorithms ;
- Good knowledge of programming languages with a proved experience is a plus.
Application:
The application should include a brief description of research interests and past experience, a CV, degrees and grades, a copy of Master thesis (or a draft thereof), motivation letter (short but pertinent to this call), relevant publications, and other relevant documents. Candidates are encouraged to provide letter(s) of recommendation and contact information to reference persons. Please send your application in one single pdf to
The deadline for the application is July 15th, 2014, but we encourage the applicants to contact us as soon as possible. The final decision will be communicated in the beginning of August.
Duration: 3 years (a full time position) Starting date: September, 2014
Supervisors: Massih-Reza Amini (UJF/LIG, France), Eric Gaussier (UJF/LIG, France), Guillaume Vernat (COFFREO, France)
Working Environment:
The PhD candidate will work at AMA team (http://ama.liglab.fr/) of the Laboratoire d'Informatique de Grenoble (LIG) lab, a leading Computer Science in France and COFFREO (https://www.coffreo.com/) a French leading Firm in electronic safe. Grenoble is the capital of the Alps in France, with excellent train connection to Geneva (2h), Paris (3h) and Turin (4h). AMA team is a dynamic group working in Machine Learning and connected scientific domains over 20 researchers (including PhD students) and that covers several aspects of machine learning from theory to applications, including statistical learning, data-mining, and cognitive science.
Benefits:
* Duration 36 months – (3 weeks a month at Grenoble and 1 week a month at Clermont Ferrand)
* Starting date of the contract : September 2014,
* Salary after taxes: from 21264 € per year,
* Possibility of French courses Help for housing Participation for public transport Scientific Resident card and help for husband/wife visa
__._,_.___
Tidak ada komentar:
Posting Komentar