@InProceedings{stymne-EtAl:2018:Short,
  author    = {Stymne, Sara  and  de Lhoneux, Miryam  and  Smith, Aaron  and  Nivre, Joakim},
  title     = {Parser Training with Heterogeneous Treebanks},
  booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},
  month     = {July},
  year      = {2018},
  address   = {Melbourne, Australia},
  publisher = {Association for Computational Linguistics},
  pages     = {619--625},
  abstract  = {How to make the most of multiple heterogeneous treebanks when training a monolingual dependency parser is an open question. We start by investigating previously suggested, but little evaluated, strategies for exploiting multiple treebanks based on concatenating training sets, with or without fine-tuning. We go on to propose a new method based on treebank embeddings. We perform experiments for several languages and show that in many cases fine-tuning and treebank embeddings lead to substantial improvements over single treebanks or concatenation, with average gains of 2.0--3.5 LAS points. We argue that treebank embeddings should be preferred due to their conceptual simplicity, flexibility and extensibility.},
  url       = {http://www.aclweb.org/anthology/P18-2098}
}