LINGUIST List 29.1500

Fri Apr 06 2018

Support: Computational Linguistics: PhD, University of Lorraine

Editor for this issue: Clare Harshey <clarelinguistlist.org>


Date: 06-Apr-2018
From: Denis Paperno <denis.papernoloria.fr>
Subject: Computational Linguistics: PhD, University of Lorraine, France
E-mail this message to a friend

Level: PhD

Institution/Organization: University of Lorraine

Duties: Research,Teaching

Specialty Areas: Computational Linguistics


Description:

Please take note of this PhD thesis offer in computational linguistics at the University of Lorraine (Nancy, France). The PhD student will have the status of a university employee with state-mandated health insurance, social security benefits and a gross monthly salary between 1676,55 and 2014,63 euros.

Title: Generating Definitions and Semantic Properties of Words with Deep Learning and Rich Lexical Resources

Summary:

The PhD thesis will consist in investigating new methods to extract appropriate semantic knowledge for a lexical unit in a given context. In particular, given a word and a context, the proposed methods will aim at automatically generating its definition as well as its semantic properties (e.g. coarse-grained sense, synonyms), adapted not only to its occurrence context, but also to the user.

With the deep learning revolution, the PhD project hypothesis is that it is now possible to fully model the task with neural networks including both the analysis of the word and its context, and the actual generation of a defining sentence in natural language. Such models would be trained from the content of lexical resources, and enriched with language models and word representations learned from large textual corpora in order to capture the lexical diversity and language style of a general audience. This approach could be very related to novel neural approaches used for machine translation or automatic summarization that both include an analysis and a generation phase.

While the topic proposed for investigation in this PhD project is related to the traditional tasks of Word Sense Disambiguation and Word Sense Induction, it is in fact more challenging as it takes a step further: a successful system is expected to generate definitions even for words and word senses that are not covered in existing lexical resources, generalizing from existing knowledge bases.

For more information, http://iaem.univ-lorraine.fr. Menu: LUE PhD Grants.

Host research units:
- Analyse et traitement informatique de la langue française (ATILF)
- Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA)
- Location: Nancy
- Grant by Lorraine Université Excellence
- Supervisors:
- Mathieu Constant (ATILF)
- Denis Paperno (LORIA)

Application:

For more information on the thesis offer, contact Mathieu Constant (Mathieu.Constantuniv-lorraine.fr) and Denis Paperno (denis.papernoloria.fr)

For applications, http://iaem.univ-lorraine.fr > menu LUE PhD Grants


Applications Deadline: 15-May-2018

Web Address for Applications: http://www.adum.fr/as/ed/voirproposition.pl?langue=fr&site=IAEM&matricule_prop=20242#version

Contact Information:
        Denis Paperno
        denis.papernoloria.fr

Page Updated: 06-Apr-2018