[Corpora-List] Open post-doctoral position in NLP at LATTICE (Paris, France)

Thierry Poibeau thierry.poibeau at ens.fr
Fri Jun 24 15:45:26 CEST 2016


Post-Doctoral position in NLP in Paris (LATTICE, ENS, Paris-Sciences-Lettres)

The research center LATTICE in Paris calls for applications for a one year postdoctoral position in natural language processing (NLP) in the framework of the research project LAKME, funded by the university cluster Paris-Sciences-Lettres.

The aim of this project is the development of algorithms for syntactic analysis of morphology rich languages. We are looking for a motivated young researcher who can imagine innovative solutions to complex problems. Prior experience in natural language (esp. tagging and parsing morphology-rich languages) and at least basic knowledge of one of the languages below -- see at the end of the email -- is necessary.

The larger goal is to work on data related to ancient languages for which there currently is no gold standard or readily available representative datasets. Corpora for training and developing experiments will be provided, but the candidate may have to develop new strategies to evaluate the work done and compare it to other approaches. The candidate may have to work on language specialists to adapt the develop techniques to specific languages or corpora.

The call for the position will remain open until filled. Interested candidates are requested to send a CV as soon as possible to Thierry Poibeau (thierry.poibeau at ens.fr <mailto:thierry.poibeau at ens.fr>). The position starts October 1, 2016.

Requirements: * Experience in natural language processing * Skills in tagging / parsing, esp. of morphology-rich languages would be a strong asset * Basic knowledge of one of the language below (Hebrew is a priority, Aramaic comes second and Uralic languages third). * Fluent English

1. Mishnaic Hebrew

The aim of this project is the development of algorithms for syntactic analysis of Classical Rabbinic Hebrew (Mishnah) in a project undertaken in collaboration with the chair for Hebrew and Aramaic at the EPHE and with the Institute of Advanced Studies (Paris).

For this position, at least basic knowledge of Hebrew is required. A strong track record of publication would be appreciated.

2. Talmudic Aramaic

In this project, the aim is to develop algorithms for automatic morphological and lexical tagging of Babylonian Aramaic. The project is undertaken in collaboration with the chair for Hebrew and Aramaic at the EPHE with the Institute of Advanced Studies (Paris) and with the editor of the Comprehensive Aramaic Lexicon at Hebrew Union College.

3. Uralic languages

In this project, the aim is to develop algorithms for automatic morphological and lexical tagging of one of the Uralic languages, preferably a under resourced one. -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 3622 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20160624/8aa3df4f/attachment.txt>



More information about the Corpora mailing list