[DBWorld] Postdoc Position on named entities and uncertainty extraction at CNAM Paris, France

************************************************************************
Extraction of named entities and uncertainty in prosopographic databases
************************************************************************

** Scientific context **

The DAPHNE ANR project aims at formalizing knowledge used by historians for=
 prosopographic
analyses (such as careers of historical figures), and at precising the cond=
itions in which parts of the
hypothesis development and validation may be automatized. The project tight=
ly associates academic
partners specialists in pattern mining, database querying, data quality in =
information systems, as well
as historians studying academics from the 13th to 15th centuries.
The Studium Parisiense (http://studium.univ-paris1.fr/) project contains mo=
re than 17,000 records with careers of academic
figures. Those records are based on factoids, i.e., proto-facts mentioned b=
y sources. When a factoid
reaches a certain degree of reliability (for instance, because several sour=
ces support it), it is called a
fact. Those data were recorded over a long period, with formating rules ada=
pted to historical work.
The first steps of the project focused on elaborating a data model to captu=
re the main concepts
from prosopographic work, and a set of rules to rate the reliability of sou=
rces and the credibility of
information [2].

** Project description **

The ISID team (http://cedric.cnam.fr/lab/equipes/isid/) has strong skills i=
n modeling and data management and has already proposed a
data model incorporating uncertainty for prosopographic databases. Initiall=
y, the post-doctorate will
consist in finalizing the modeling proposed in [1, 3] in order to propose a=
 method of representation and
management of data adapted to the production and validation of historical k=
nowledge, integrating
the notion of uncertainty, credibility of sources and authors. The objectiv=
e will then be to propose a
method of recognition of named entities (NER) adapted to historical prosopo=
graphic data. However,
the difficulty here is twofold. First of all, these data are by nature ofte=
n imprecise/uncertain (end
of the 13th century, Easter 1243, summer 1312, in Piemont, near Paris, sout=
h of the Duchy of
Burgundy), incomplete (we do not know what a given university student did b=
etween two dates, we
do not know in which university he studied theology), even inconsistent or =
unreliable. But moreover,
most of the facts and places are temporally contextualized : for example, F=
landers are independant
in the 11th century while they were Burgundian in the 14th century, the ter=
ritories of bishoprics and
feudal authorities, moreover often formed of non-contiguous zones, etc. The=
se two aspects make it
difficult to identify named entities on this data using classic tools like =
CoreNLP, spaCy
or NLTK.

Finally, the last objective of this post-doctorate will consist in extracti=
ng and quantifying the
uncertainty relating to the various data, including the information concern=
ing the entities resulting
from the identification technique proposed in the first part of the post-do=
ctorate. This approach may,
depending on the progress of the post-doctorate, be supplemented by the dev=
elopment of inference
rules in order to evaluate the uncertainty of data related to those for whi=
ch an uncertainty has been
extracted. This uncertainty can then be used during subsequent phases of th=
e Daphn=C3=A9 project, in
particular for questioning or extracting hypotheses.

** Candidate background **

=E2=80=A2 PhD in computer science
=E2=80=A2 good level with knowledge databases (ontology, NLP, NER)
=E2=80=A2 proficient programming skills (Java, Python)
Feel free to apply even if you do not have precisely all the mentioned skil=
ls.

** Workplace, dates, salary **

=E2=80=A2 The candidate will be integrated in the ISID team (C=C3=89DRIC la=
b at CNAM Paris), under the
superivision of C=C3=A9dric du Mouza, Jacky Akoka and Isabelle Wattiau. Off=
ices are located in the
center of Paris. Due to the ongoing pandemic, the beginning of the contract=
 (at least) will be
potentially be remote.
=E2=80=A2 One-year contract, with a starting date in September 2021, if pos=
sible.
=E2=80=A2 The net salary will be around 2,500 euros per month.

** Contact **

Please send your application with a resume at the following addresses :
[email protected], [email protected] and isabelle.wattiau-t4/[email protected]

** R=C3=A9f=C3=A9rences **

[1] J. Akoka, I. Comyn-Wattiau, S. Lamass=C3=A9, and C. du Mouza. Modeling =
historical social networks databases.
In T. Bui, editor, 52nd Hawaii International Conference on System Sciences,=
 HICSS 2019, Grand
Wailea, Maui, Hawaii, USA, January 8-11, 2019, pages 1=E2=80=9310, 2019.
[2] J. Akoka, I. Comyn-Wattiau, S. Lamass=C3=A9, and C. du Mouza. Contribut=
ion of conceptual modeling to enhancing
historians=E2=80=99 intuition - application to prosopography. In Conceptual=
 Modeling - 39th International
Conference, ER, 2020.
[3] J. Akoka, I. Comyn-Wattiau, S. Lamass=C3=A9, and C. Du Mouza. Conceptua=
l modeling of prosopographic
databases integrating quality dimensions. Journal of Data Mining and Digita=
l Humanities, 2021.
_______________________________________________
Please do not post msgs that are not relevant to the database community at =
large.  Go to www.cs.wisc.edu/dbworld for guidelines and posting forms.
To unsubscribe, go to https://lists.cs.wisc.edu/mailman/listinfo/dbworld