Data Augmentation for Context-Sensitive Neural Lemmatization Using Inflection Tables and Raw Text

@article{Bergmanis2019DataAF,
  title={Data Augmentation for Context-Sensitive Neural Lemmatization Using Inflection Tables and Raw Text},
  author={Toms Bergmanis and Sharon Goldwater},
  journal={CoRR},
  year={2019},
  volume={abs/1904.01464}
}
Lemmatization aims to reduce the sparse data problem by relating the inflected forms of a word to its dictionary form. Using context can help, both for unseen and ambiguous words. Yet most context-sensitive approaches require full lemma-annotated sentences for training, which may be scarce or unavailable in lowresource languages. In addition (as shown here), in a low-resource setting, a lemmatizer can learn more from n labeled examples of distinct words (types) than from n (contiguous) labeled… CONTINUE READING
11
Twitter Mentions

References

Publications referenced by this paper.
SHOWING 1-10 OF 21 REFERENCES

Exploring Context Representations for Neural Lemmatisation Moses : Open source toolkit for statistical machine translation

Peter Makarov, Simon Clematide
  • 2018
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Exploring Context Representations for Neural Lemmatisation

Faheem Kirefu.
  • Master’s thesis, University of Edinburgh.
  • 2018
VIEW 1 EXCERPT

Similar Papers

Loading similar papers…