Emc^Sci

New: Francesco Osborne (Knowledge Media institute, The Open University) will be the keynote speaker

The Program is online

22/06: The Proceedings are online

Scope

Extracting knowledge from text, also known as text mining, is a key task in the context of Natural Language Processing. Text analysis techniques allow to identify concepts and relations between such concepts in unstructured texts.

Scientific texts constitute a challenging and interesting application field for such techniques: finding key concepts, identifying research areas and the relations between them [Lopez 2010, Gabor 2016b] allow to improve the access to scientific text collections [Osborne 2012, Osborne 2013]. The fact that papers have a set of associated metadata allows us to extract collaboration information [Roth 2010] as well as other information that can be represented as a knowledge graph [Nuzzolese 2016] and also determine the evolution of certain concepts in time [Chavalarias 2013]. Knowledge extraction may also be used for automating discovery science [Kitano 2016], a grand challenge of future AI systems.

The interest in this kind of knowledge extraction is testified by the recent appearance of dedicated workshops and challenges, such as SAVE-SD (http://cs.unibo.it/save-sd/2015/ ) and ScienceIE (task 10 at Semeval 2017: https://scienceie.github.io/index.html), as well as emerging projects promoted by prominent publishers such as SpringerNature SciGraph and Elsevier Labs and from the scientific communities such as the Scholarly Data portal and Open Citations.

The objective of this workshop is to put together researchers that are interested in various aspects of the process of extracting knowledge from scientific text, in particular but not limited to: expert and community finding based on social networks, discovering research trends, methods for the extraction of key phrases and relations, automatic construction or expansion of ontologies dedicated to the analysis of scholar data.

Topics of Interest:

• Keyphrase and/or relation extraction from scientific texts;
• Semantic similarity between scientific concepts;
• Identification of experts;
• Semantic Information Retrieval;
• Citation analysis and prediction;
• Ontologies for the description of scientific domains;
• Enrichment of Ontologies with scientific concepts and relations;
• Automatic summarization;
• Making sense of research dynamics (evolution of concepts, communities, identification of “forgotten domains” or emerging research fields);
• Discovery science.

Bibliography:

[Chavalarias 2013] David Chavalarias et Jean-Philippe Cointet. “Phylomemetic patterns in science evolution - the rise and fall of scientific fields”. PLOS ONE, 8(2).

[Nuzzolese 2016] Andrea Giovanni Nuzzolese, Anna Lisa Gentile, Valentina Presutti, Aldo Gangemi: Conference Linked Data: The ScholarlyData Project. International Semantic Web Conference (2) 2016: 150-158

[Gabor 2016a] Gabor K., Zargayouna H., Buscaldi D., Tellier I., Charnois T. Semantic Annotation of the ACL Anthology Corpus for the Automatic Analysis of Scientific Literature. In: LREC 2016. Portorose, Slovenia.

[Gabor 2016b] Gábor K., Zargayouna H., Tellier I., Buscaldi D., Charnois T. Unsupervised Relation Extraction in Specialized Corpora Using Sequence Mining. IDA 2016: 237-248

[Lopez 2010] Patrice Lopez and Laurent Romary. 2010. HUMB: Automatic key term extraction from scientific articles in GROBID. In Proceedings of the 5th International Workshop on Semantic Evaluation (SemEval '10). Association for Computational Linguistics, Stroudsburg, PA, USA, 248-251.

[Osborne 2012] Francesco Osborne et Enrico Motta. “Mining semantic relations between research areas”. In : International Semantic Web Conference (ISWC2012). Springer Berlin Heidelberg, 2012. p. 410-426.

[Osborne 2013] Francesco Osborne, Enrico Motta et Paul Mulholland. “Exploring scholarly data with rexplore”. In : International Semantic Web Conference (ISWC2013). Springer Berlin Heidelberg, 2013. p. 460-477.

[Roth 2010] Camille Roth et Jean-Philippe Cointet. “Social and semantic coevolution in knowledge networks” Social Networks 32.1 (2010): 16-29.

[Kitano 2016] Hiroaki Kitano: Artificial Intelligence to Win the Nobel Prize and Beyond: Creating the Engine for Scientific Discovery. AI Magazine 37(1): 39-49 (2016)