Current Activities
CoNLL-2015 Shared Task on Shallow Discourse Parsing
I am co-organizing the CoNLL-2015 shared task on shallow discourse parsing using the Penn Discourse Treebank (PDTB) v2.0. This tasks takes the CoNLL tradition to the next level of discourse phenomena after coreference.
I am co-organizing the SemEval-2015 shared task on analysis of clinical text. This task is a follow on to the one organized at SemEval-2014, Task 7. The purpose of these tasks is to enhance current research in natural language processing methods used in the clinical domain. The second aim of the task is to introduce clinical text processing to the broader NLP community. The task aims to combine supervised methods for text analysis with unsupervised approaches. More specifically, the task aims to combine supervised methods for entity/acronym/abbreviation recognition and mapping to UMLS CUIs (Concept Unique Identifiers), identifying various attributed associated with those CUIs and normalizing their values. We are continuing to promote the use of larger clinical corpora for investigating into unsupervised techniques.
Past Activities
I am co-organizing the SemEval-2014 shared task on analysis of clinical text. The purpose of this task is to enhance current research in natural language processing methods used in the clinical domain. The second aim of the task is to introduce clinical text processing to the broader NLP community. The task aims to combine supervised methods for text analysis with unsupervised approaches. More specifically, the task aims to combine supervised methods for entity/acronym/abbreviation recognition and mapping to UMLS CUIs (Concept Unique Identifiers) with access to larger clinical corpus for utilizing unsupervised techniques.
I chaired the organization of CoNLL-2012 Shared Task on Modeling Multilingual Unrestricted Coreference in OntoNotes. It was also received quite well. There were a total of 16 participants from 6 countries. We provided participants with gold standard and predicted information on almost all the layers of OntoNotes in all three languages — English, Chinese and Arabic, except coreference, and the task was to identify corefering mentions and cluster them into entities. CoNLL-2012 was colocated with ACL/EMNLP-2012 in Jeju, Korea.
I chaired the organization of CoNLL-2011 Shared Task on Modeling Unrestricted Coreference in OntoNotes. It was received quite well. There were a total of 23 participants from 11 countries. We provided participants with gold standard and predicted information on all the layers of OntoNotes except coreference, and the task was to identify corefering mentions and cluster them into entities. CoNLL-2011 was colocated with ACL/HLT-2011 in Portland.
I co-chaired 2011 Lingustic Annotation Workshop which was also collocated with ACL in Portland.
SemEval-2007, Task 17: English Lexical Sample, SRL and All Words
I co-organized Task 17 in the first SemEval which was held in 2007. The task was focused on word sense disambiguation and semantic role labeling. The dataset for this task can be downloaded here. |
