The Labex EFL project (Empirical Foundations of Linguistics,
http://www.labex-efl.org/) is seeking to fill a postdoctoral research
position in NLP/Knowledge Extraction. The position is for 12 months
(full time), starting as soon as possible.

Topic

Semantic relation extraction is a key component in identifying
domain-specific knowledge in text and structuring it into knowledge
bases. While supervised, neural network based methods (RNNs and CNNs)
perform well on domain-specific relation extraction, this scenario is
limited to pre-defined types of semantic relations. Therefore,
adapting relation extraction to a new domain requires to have at least
a skeleton of a domain ontology with relation types. Our goal is to
further research into acquiring domain-specific relation types and
instances directly from corpora with as minimal supervision as
possible.

In previous work, we explored the strengths and limitations of both
pattern-based [1] and DSM-based [2] approaches to unsupervised
relation extraction. Depending on the profile of the candidate, the
follow-ups that can be considered include :

- improving pattern-based methods for relation extraction,
- joint entity and relation extraction in specialized domains,
- unsupervised or weakly supervised relation extraction,
- knowledge base population with relation instances.

Context:

The post is funded by the Labex EFL project, strand 5: Computational
semantic analysis. The candidate will be jointly affiliated to the
LIPN Computer Science Lab (http://lipn.univ-paris13.fr/en/laboratory)
at Paris 13 University, and the ERTIM NLP lab (http://www.er-tim.fr)
at INALCO. The position is part of an ongoing interdisciplinary
research project on text mining and knowledge extraction (see
bibliography).


Selection Criteria:

- PhD in computer science
- experience and/or interest in:
   - natural language processing  
   - text mining and machine learning (experience in deep learning is a plus)
   - knowledge engineering and the semantic web
- good writing skills


The position is open until filled. To apply, send to Haďfa Zargayouna
(haifa.zargayouna@lipn.univ-paris13.fr) and Kata Gábor
(kata.gabor@inalco.fr)
 
- a detailed CV (with a list of publications)
- a cover letter
- names and email of two referees

Informal inquiries can also be addressed to
haifa.zargayouna@lipn.univ-paris13.fr or kata.gabor@inalco.fr


Bibliography

[1] Gábor K., Zargayouna H., Buscaldi D., Tellier I., Charnois
T. (2016) : Unsupervised Relation Extraction in Specialized Corpora
Using Sequence Mining. IDA 2016, LNCS 9897, p.237-248.

[2] Gábor K, Zargayouna H, Tellier I, Buscaldi D, Charnois T:
Exploring Vector Spaces for Semantic Relations. In: EMNLP 2017.

[3] Gábor K., Zargayouna H., Tellier I., Buscaldi D., Charnois
T. (2016) : A Typology of Semantic Relations Dedicated to Scientific
Literature Analysis. SAVE-SD Workshop at the 25th WWW Conference.

[4] Gábor K., Zargayouna H., Buscaldi D., Tellier I., Charnois
T. (2016) : Semantic Annotation of the ACL Anthology Corpus for the
Automatic Analysis of Scientific Literature. In: LREC 2016.

[5] Gábor K., Buscaldi D., Schumann A-K., QasemiZadeh B., Zargayouna
H., Charnois T.: Semeval-2018 Task 7: Semantic Relation Extraction and
Classification in Scientific Papers. In International Workshop on
Semantic Evaluation (SemEval-2018).