Training Dependency Parsers with Partial Annotation

@article{Li2016TrainingDP,
  title={Training Dependency Parsers with Partial Annotation},
  author={Zhenghua Li and Yue Zhang and Jiayuan Chao and Min Zhang},
  journal={ArXiv},
  year={2016},
  volume={abs/1609.09247}
}
Recently, these has been a surge on studying how to obtain partially annotated data for model supervision. However, there still lacks a systematic study on how to train statistical models with partial annotation (PA). Taking dependency parsing as our case study, this paper describes and compares two straightforward approaches for three mainstream dependency parsers. The first approach is previously proposed to directly train a log-linear graph-based parser (LLGPar) with PA based on a forest… CONTINUE READING
1
Twitter Mention

Citations

Publications citing this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 38 REFERENCES

Discriminative trai

Michael Collins
  • 2002
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Dependency Parsing (Synthesis

kim Nivre
  • 2009
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Parse imputation for dependency annotations

Alexis Nasr
  • 2015

An experimental comparison

hierry Artières
  • 2014
VIEW 2 EXCERPTS

An experimental comparison of active learning strategies for partially labeled sequences

Andre Martins, Miguel Almeida, Noah A. Smith
  • Proceedings of EMNLP
  • 2014

Similar Papers

Loading similar papers…