[Corpora-List] EMNLP workshop announcement: LOUHI 2015, September 17th, Lisbon, Portugal

Cyril Grouin cyril.grouin at limsi.fr
Wed Sep 2 14:45:25 CEST 2015

[Apologies for multiple postings]


EMNLP 2015 Workshop - The Sixth International Workshop on Health Text Mining and Information Analysis (Louhi 2015) http://louhi2015.limsi.fr

Location: EMNLP 2015, in Lisbon, Portugal (September 17, 2015)

** Background **

The Sixth International Workshop on Health Text Mining and Information Analysis provides an interdisciplinary forum for researchers interested in automated processing of health documents. Health documents encompass electronic health records, clinical guidelines, spontaneous reports for pharmacovigilance, biomedical literature, health forums/blogs or any other type of health related documents. The Louhi workshop series fosters interactions between the Computational Linguistics, Medical Informatics and Artificial Intelligence communities. It started in 2008 in Turku, Finland and has been organized five times: Louhi 2010 was co-located with NAACL in Los Angeles, CA; Louhi 2011 was co-located with Artificial Intelligence in Medicine (AIME) in Bled, Slovenia; Louhi 2013 was held in Sydney, Australia during NICTA Techfest; and Louhi 2014 was co-located with EACL in Gothenburg, Sweden.

** Invited Speaker **

Pr Marie-Francine Moens, Department of computer Science, Katholieke Universiteit Leuven

Among the application domains of information extraction, the biomedical domain is one of the most important ones. This is due to the large amount of biomedical text sources including the vast scientific literature and collections of patient reports written in natural language. These sources contain a wealth of crucial knowledge that needs to be mined. Typical mining tasks regard entity recognition, entity-relation extraction, and event and event participant recognition. Recently we witness an interest in the recognition of spatial relationships between entities and of temporal relationships between events. One of the most important problems in information extraction regards dealing with a limited amount of examples that are manually annotated by experts and that can be used for training the extraction models.

In this talk we discuss how we can leverage knowledge contained in unlabelled texts and ontological knowledge about known relationships between the output labels used for the extractions. The former aspect especially focuses on how to automatically create novel training examples from the unlabelled data, the latter on how to integrate the relationships in models for structured machine learning during training and testing of the extraction models in the most efficient way. We show promising results and point to directions of future research.

** Program **

Thursday, September 17, 2015

09:00-10:30 / Session I - Corpus creation - Room 3 - Yim WW, Kwan S and Yetisgen M. In-depth annotation for patient level liver cancer staging. - Sadeque F, Solorio T, Pedersen T, Shrestha P and Bethard S. Predicting Continued Participation in Online Health Forums. - D’hondt E, Tannier X and Névéol A. Redundancy in French Electronic Health Records: A preliminary study. - Grouin C, Griffon N and Névéol A. Is it possible to recover personal health information from an automatically de-identified corpus of French EHRs?

11:00-12:30 / Session II - Poster - Alfalahi A, Skeppstedt M, Ahlbom R, Baskalayci R, Henriksson A, Asker L, Paradis C and Kerren A. Expanding a dictionary of marker words for uncertainty and negation using distributional semantics. - Busse S. Checking a structured pathology report for completeness of content using terminological knowledge. - Cocos A, Masino A, Qian T, Pavlick T and Callison-BurchC. Effectively Crowdsourcing Radiology Report Annotations. - Cruz Diaz NP and Mańa López M. An Analysis of Biomedical Tokenization: Problems and Strategies. - Dwi Prasetyo N, Hauff C, Nguyen D, van den Broek T and Hiemstra D. On the Impact of Twitter-based Health Campaigns: A Cross-Country Analysis of Movember. - Mitchell J and Steedman M. Parser Adaptation to the Biomedical Domain without Re-Training. - Roller R and Stevenson M. Held-out versus Gold Standard: Comparison of Evaluation Strategies for Distantly Supervised Relation Extraction from Medline abstracts. - Segura-Bedmar I, Suárez-Paniagua V and Martínez P. Exploring Word Embedding for Drug Name Recognition. - Weegar R and Dalianis H. Creating a rule based system for text mining of Norwegian breast cancer pathology reports. - Yetisgen M, Klassen P, McCarthy L, Pellicer E, Payne T and Gunn M. Annotation of Clinically Important Follow-up Recommendations in Radiology Reports. - Zheng J and Yu H. Identifying Key Concepts from EHR Notes Using Domain Adaptation.

12:30-14:00 / Lunch break

14:00-15:30 / Session III - Invited talk - Room 3 - Marie-Francine Moens. Information Extraction from Biomedical Texts: Learning Models with Limited Supervision.

16:00-17:30 / Session IV - Corpus processing - Room 3 - Friedrich S and Dalianis H. Adverse Drug Event classification of health records using dictionary based pre-processing and machine learning. - Venturi G, Bellandi T, Dell’Orletta F and Montemagni S. NLP-Based Readability Assessment of Health-Related Texts: a Case Study on Italian Informed Consent Forms. - Jagannatha A, Chen J and Yu H. Mining and Ranking Biomedical Synonym Candidates from Wikipedia. - Henriksson A. Representing Clinical Notes for Adverse Drug Event Detection.

** Organizers **

Louhi 2015 is organized by the ILES Group at LIMSI-CNRS in Orsay, France.

Chair: Cyril Grouin, LIMSI-CNRS, Orsay, France Organization committee: Thierry Hamon, LIMSI-CNRS, Orsay, France & Université Paris 13 Aurélie Névéol, LIMSI-CNRS, Orsay, France Pierre Zweigenbaum, LIMSI-CNRS, Orsay, France

** Program Committee **

Sophia Ananiadou, University of Manchester, U.K. Sabine Bergler, Concordia University, Canada Thomas Brox Rřst, Norwegian University of Science and Technology, Norway Kevin B. Cohen, University of Colorado/School of Medicine, USA Francisco Couto, University of Lisbon, Portugal Hercules Dalianis, Stockholm University, Sweden Louise Deléger, INRA, France Gaël Dias, Normandie University, France Martin Duneld/Hassel, Stockholm University, Sweden Richárd Farkas, Institute of Informatics, Hungary Filip Ginter, University of Turku, Finland Natalia Grabar, CNRS UMR 8163, STL Université de Lille 3, France Gintaré Grigonyté, Stockholm University, Sweden Aron Henriksson, Stockholm University, Sweden Rezarta Islamaj, NIH/NLM/NCBI, USA Antonio Jimeno Yepes, IBM Research, Australia Jussi Karlgren, KTH, Royal Institute of Technology, Sweden Dimitrios Kokkinakis, University of Gothenburg, Sweden Maria Kvist, Stockholm University, Sweden Alberto Lavelli, Fondazione Bruno Kessler, Italy David Martinez, University of Melbourne and MedWhat.com, Australia Beáta Megyesi, Uppsala University, Sweden Marie-Jean Meurs, UQAM & Concordia University, QC, Canada Fleur Mougin, Université de Bordeaux, ERIAS, Centre INSERM U897, ISPED, France Danielle L Mowery, University of Utah, USA Henning Müller, University of Applied Sciences Western Switzerland, Switzerland Mariana Neves, Hasso-Plattner-Institute at the University of Potsdam, Germany Jong C. Park, KAIST Computer Science, Korea Jon D. Patrick, Health Language Laboratories, Australia Sampo Pyysalo, University of Turku, Finland Stefan Schulz, Graz General Hospital and University Clinics, Austria Tapio Salakoski, University of Turku, Finland Sanna Salanterä, University of Turku, Finland Isabel Segura-Bedmar, Universidad Carlos III de Madrid, Spain Maria Skeppstedt, Gavagai and Linnaeus University, Sweden Hanna Suominen, NICTA, Australia Suzanne Tamang, Stanford University School of Medicine, USA Özlem Uzuner, MIT, U.S.A. Sumithra Velupillai, Stockholm University, Sweden Karin Verspoor, University of Melbourne, Australia Mats Wirén, Stockholm University, Stockholm, Sweden

Contact person: cyril.grouin A at T limsi.fr <http://limsi.fr/>

-------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 10470 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20150902/15eb6a62/attachment.txt>

More information about the Corpora mailing list