A Simple yet Effective Joint Training Method for Cross-Lingual Universal Dependency Parsing

@inproceedings{Chen2018ASY,
  title={A Simple yet Effective Joint Training Method for Cross-Lingual Universal Dependency Parsing},
  author={Danlu Chen and Mengxiao Lin and Zhifeng Hu and Xipeng Qiu},
  booktitle={CoNLL Shared Task},
  year={2018}
}
This paper describes Fudan’s submission to CoNLL 2018’s shared task Universal Dependency Parsing. We jointly train models when two languages are similar according to linguistic typology and then do an ensemble of the models using a simple re-parse algorithm. Our system outperforms the baseline method by 4.4% and 2.1% on the development and test set of CoNLL 2018 UD Shared Task, separately.1. Our code is available on https://github.com/ taineleau/FudanParser. 

References

Publications referenced by this paper.
Showing 1-10 of 11 references

Universal Dependencies 2.2. LINDAT/CLARIN digital library at the Institute of Formal and Applied Linguistics, Charles University, Prague, http: //hdl.handle.net/11234/1-1983xxx

  • Joakim Nivre
  • 2018

Tokeniz - ing , pos tagging , lemmatizing and parsing ud 2 . 0 with udpipe

  • Xingxing Zhang, Adam Lopez
  • Proceedings of the CoNLL 2017 Shared Task…
  • 2017

Similar Papers

Loading similar papers…