Low-Resource Parsing with Crosslingual Contextualized Representations

@article{Mulcaire2019LowResourcePW,
  title={Low-Resource Parsing with Crosslingual Contextualized Representations},
  author={Phoebe Mulcaire and Jungo Kasai and Noah A. Smith},
  journal={ArXiv},
  year={2019},
  volume={abs/1909.08744}
}
Despite advances in dependency parsing, languages with small treebanks still present challenges. We assess recent approaches to multilingual contextual word representations (CWRs), and compare them for crosslingual transfer from a language with a large treebank to a language with a small or nonexistent treebank, by sharing parameters between languages in the parser itself. We experiment with a diverse selection of languages in both simulated and truly low-resource scenarios, and show that… CONTINUE READING

References

Publications referenced by this paper.
SHOWING 1-10 OF 61 REFERENCES

CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies

VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Enriching Word Vectors with Subword Information

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Many Languages, One Parser

VIEW 8 EXCERPTS

AllenNLP: A Deep Semantic Natural Language Processing Platform

VIEW 2 EXCERPTS
HIGHLY INFLUENTIAL