Article separation in historical newspapers

Interested in joining a young group the crossroad between document
analysis and NLP, located in a historical town by the Atlantic Ocean?
And walk 10 minutes from the lab to the beach. We have open positions
in the context of 2 ongoing Horizon 2020 projects: Embeddia and
NewsEye as well as subsequent projects. In 2020-2021, we have among
others published long papers in CORE A* and A conferences ACL, JCDL,
ICDAR, CoNLL, DAS COLING, ICADL.. We coordinate the H2020 NewsEye
project, focused on improving access to large European collections of
historical newspapers. We developed the NewsEye platform for
navigating through such collections, a platform it will build upon in
future years. Full details on the NewsEye project are available on its
website - http://newseye.eu/

Location: L3i laboratory, La Rochelle, France

Duration: 2 years (1+1), with possible further extension

Net salary range: 2100¤-2300 ¤ monthly

Context: H2020 NewsEye project and regional project Anna


Keywords: digitized documents, combination of visual and textual
features, layout analysis, statistical NLP, language-independent
approaches, deep/machine learning.

 

Applications are invited for a postdoctoral researcher position on the
separation of articles from digitized newspapers, in particular
historical newspapers. This task is a critical first step for any use
of digitized newspapers, which are initially only split per "page
image" files.

 

Your goal will be to study the state of the art and devise methods
combining visual and textual features so as improve the performance of
article separation on a large scale. In particular, we seek for
methods that function with limited training data and for several
languages. NLP and image analysis experience are equally
valued. Experience of both is ideal.


Who we search for:

- PhD in document analysis, NLP, IR, or ML, ideally followed by
        postdoctoral experience

- proven record of high-level publications in one or more of those
        fields

- fluency in written and spoken English (French language skills are
  not relevant)

 

Applications including a CV and a one-page research statement
discussing how the candidate's background fits requirements and topic
are to be sent to by email to antoine.doucet@univ-lr.fr, strictly with
the subject "NewsEye/ANNA postdoc application".

Application deadline: 13 October 2021.