Corpus ID: 218595733

Neural Polysynthetic Language Modelling

@article{Schwartz2020NeuralPL,
  title={Neural Polysynthetic Language Modelling},
  author={Lane Schwartz and Francis M. Tyers and Lori S. Levin and C. Kirov and Patrick Littell and Chi-kiu Lo and Emily Prudhommeaux and Hyunji Hayley Park and K. Steimel and R. Knowles and J. Micher and Lonny Strunk and H. Liu and Coleman Haley and Katherine J. Zhang and Robbie Jimmerson and Vasilisa Andriyanets and Aldrian Obaja Muis and Naoki Otani and Jong Hyuk Park and Zhisong Zhang},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.05477}
}
Research in natural language processing commonly assumes that approaches that work well for English and and other widely-used languages are "language agnostic". In high-resource languages, especially those that are analytic, a common approach is to treat morphologically-distinct variants of a common root as completely independent word types. This assumes, that there are limited morphological inflections per root, and that the majority will appear in a large enough corpus, so that the model can… Expand
4 Citations

References

SHOWING 1-10 OF 109 REFERENCES
What Kind of Language Is Hard to Language-Model?
A General Computational Model For Word-Form Recognition And Production
The Nunavut Hansard Inuktitut-English Parallel Corpus 3.0 with Preliminary Machine Translation Results
Using the Nunavut Hansard Data for Experiments in Morphological Analysis and Machine Translation
Data-Driven Morphological Analysis for Uralic Languages
...
1
2
3
4
5
...