tensorflowAMR

Two applications of character-level seq2seq RNN translation.

Contents

SemEval2016 - AMR Parsing with character-level seq2seq RNN.
LREC2016 - character-level English-Latvian seq2seq RNN translation.

Description

For details see:

@InProceedings{gbarzdins-dgosko:2016:NAACL-HLT,
  author    = {Barzdins, Guntis and  Gosko, Didzis},
  title     = {RIGA: Impact of Smatch Extensions and Character-Level Neural Translation on AMR Parsing Accuracy},
  booktitle = {Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
  month     = {June},
  year      = {2016},
  address   = {San Diego, California},
  publisher = {Association for Computational Linguistics},
  pages     = {to appear},
  url       = {to appear}
}

@InProceedings{gbarzdins-srenals-dgosko:2016:LREC,
  author    = {Barzdins, Guntis, Renals, Steve and  Gosko, Didzis},
  title     = {Character-level Neural Translation for Multilingual Media Monitoring in the SUMMA Project},
  booktitle = {10th edition of the Language Resources and Evaluation Conference},
  month     = {May},
  year      = {2016},
  address   = {Portorož, Slovenia},
  publisher = {LREC},
  pages     = {to appear},
  url       = {to appear}
}