@inproceedings{baldewein04:_seman_role_label_chunk_sequen,
  abstract = {We describe a statistical approach to semantic role labelling that employs only shallow infor- mation. We use a Maximum Entropy learner, augmented by EM-based clustering to model the fit between a verb and its argument can- didate. The instances to be classified are se- quences of chunks that occur frequently as ar- guments in the training corpus. Our best model obtains an F score of 51.70 on the test set.},
  added-at = {2017-04-03T19:28:28.000+0200},
  address = {Boston, MA},
  author = {Baldewein, Ulrike and Erk, Katrin and Padó, Sebastian and Prescher, Detlef},
  biburl = {https://puma.ub.uni-stuttgart.de/bibtex/27dbf7126b761b72dc36f5ac70aa42d1b/sp},
  booktitle = {Proceedings of the CoNLL 2004 shared task},
  interhash = {41ca151c718301d2c6a9419f0569eca0},
  intrahash = {7dbf7126b761b72dc36f5ac70aa42d1b},
  keywords = {conference myown},
  timestamp = {2024-02-22T12:36:52.000+0100},
  title = {Semantic Role Labelling for Chunk Sequences},
  url = {http://www.aclweb.org/anthology/W/W04/W04-2413.pdf},
  year = 2004
}