Bibliographie
"Third Edition of the Workshop on Interactions between Data Mining and
Natural Language Processing"
(DMNLP 2016)
ECML/PKDD 2016 Workshop
September 23, 2016, Riva Del Garda, Italy
* * * * * * * * * * * * * * * * * * * * * * * * * * ** * * * * * * * * *
SCOPE
On the one hand, in the field of Natural Language Processing (NLP),
numerical Machine Learning methods (e.g., SVM, CRF) have been
intensively explored and applied. Despite the good results obtained by
the numerical methods, one major drawback is that they do not provide a
human readable model. A promising direction is the integration of
symbolic knowledge.
On the other hand, research in Data Mining has progressed significantly
in the last decades, through the development of advanced algorithms and
techniques to extract knowledge from data in different forms. In
particular, for two decades Pattern Mining has been one of the most
active field in Knowledge Discovery.
Recently, a new field has emerged taking benefit of both domains : Data
Mining and NLP. The objective of DMNLP is thus to provide a forum to
discuss how Data Mining can be interesting for NLP tasks, providing
symbolic knowledge, but also how NLP can enhance data mining approaches
by providing richer and/or more complex information to mine and by
integrating linguistics knowledge directly in the mining process.
The workshop aims at bringing together researchers from both communities
in order to stimulate discussions about the cross-fertilization of those
two research fields. The idea of this workshop is to discuss future
directions and new challenges emerging from the cross-fertilization of
Data Mining and NLP and in the same time initiate collaborations between
researchers of both communities.
CALL FOR PAPERS
The workshop promotes works where the two following dimensions are
combined in one as symbiosis.
The first dimension is Data Mining, for instance Pattern Mining
(itemsets, sequences, trees, graphs, association rules), classification
(decision trees, FCA,...), inductive logic programming.
The second dimension is NLP, for example question/answering systems,
translation, information extraction, linguistic analysis (lexical
analysis, terminology, syntax, semantics, discourse, stylistics),
classification, knowledge extraction/ontology building from texts,
information retrieval, corpus annotation, social/opinion mining.
A list of non-exhaustive topics that fit the scope of the workshop is
thus :
- Pattern discovery for NLP
- Constraint-based pattern mining in text
- Data mining query languages for expressing NLP tasks
- Data representation (sequence, tree, graphs) for NLP
- Text modeling for Data Mining
- Mining complex data for / coming from NLP
- Representation learning in NLP (e.g., deep learning, compositional
models...)
- Relationships between data mining and NLP
- Modeling and visualizing data mining results on text
- Integrating NLP characteristics in data mining
- Data mining approaches for linguistic knowledge building
- Knowledge discovery for linguistic analysis (e.g. stylistics,
socio-linguistics,…)
- Knowledge-based data mining for NLP (e.g., ontologies, linked open
data...)
Our main goal is to stimulate discussion, collaboration and the sharing
of experiences.
In that respect, we would have three submission types :
- unpublished works (max 8 pages, double submissions allowed)
- extended abstracts and vision statements (max 4 pages)
- recently published works (special oral-only track, no page limits)
For more details on submission, see the DMNLP webpage at
http://dmnlp.loria.fr
IMPORTANT DATES
Paper submission deadline : Tuesday, June 21, 2016
Author notification : Monday, July 8, 2016
Final version : Sunday, July 24, 2015
ORGANIZATION
- Peggy Cellier, INSA Rennes, IRISA, Rennes, France
- Thierry Charnois, Université de Paris 13, LIPN, France
- Andreas Hotho, University of Würzburg, Germany
- Stan Matwin, Dalhousie University, Canada
- Marie-Francine Moens, Katholieke Universiteit, Leuven, Belgium
- Yannick Toussaint, INRIA, LORIA, Vandoeuvre-les-Nancy, France