The clinical text mining group had three papers at workshops of this years ACL conference in Sofia. We had two papers at the BioNLP workshop (“Corpus-Driven Terminology Development: Populating Swedish SNOMED CT with Synonyms Extracted from Electronic Health Records” by Aron Henriksson, Maria Skeppstedt, Maria Kvist, Martin Duneld and Mike Conway and “Adapting a parser to clinical text by simple pre-processing rules” by Maria Skeppstedt) and a paper at the ACL student research workshop (“Annotating named entities in clinical text by combining pre-annotation and active learning” by Maria Skeppstedt).
Among the papers which I found most interesting at the conference were: “Improving Text Simplification Language Modeling Using Unsimplified Text Data” by David Kauchak, as well as the winner of the student paper competition: “A corpus-based evaluation method for Distributional Semantic Models” by Abdellah Fourtassi and Emmanuel Dupoux. Interesting workshop paper were: “Analysis of Stopping Active Learning based on Stabilizing Predictions” by Michael Bloodgood and John Grothendieck and “Towards Dynamic Word Sense Discrimination with Random Indexing” by Hans Moen, Erwin Marsi and Björn Gambäck.
Conference venue
At the conference dinner, a dance group performed traditional bulgarian folk dances and also taught us some of the dance steps.
The last day of the conference, many of the conference participants joined a walking tour, in which we were shown some of the many beautiful historic buildings of Sofia.