Better Morphology Prediction for Better Speech Systems

Dravyansh Sharma, Melissa Wilson, Antoine Bruguier


Prediction of morphological forms is a well-studied problem and can lead to better speech systems either directly by rescoring models for correcting morphology, or indirectly by more accurate dialog systems with improved natural language generation and understanding. This includes both lemmatization, i.e. deriving the lemma or root word from a given surface form as well as morphological inflection, i.e. deriving surface forms from the lemma. We train and evaluate various language-agnostic end-to-end neural sequence-to-sequence models for these tasks and compare their effectiveness. We further augment our models with pronunciation information which is typically available in speech systems to further improve the accuracies of the same tasks. We present the results across both morphologically modest and rich languages to show robustness of our approach.


 DOI: 10.21437/Interspeech.2019-3207

Cite as: Sharma, D., Wilson, M., Bruguier, A. (2019) Better Morphology Prediction for Better Speech Systems. Proc. Interspeech 2019, 3535-3539, DOI: 10.21437/Interspeech.2019-3207.


@inproceedings{Sharma2019,
  author={Dravyansh Sharma and Melissa Wilson and Antoine Bruguier},
  title={{Better Morphology Prediction for Better Speech Systems}},
  year=2019,
  booktitle={Proc. Interspeech 2019},
  pages={3535--3539},
  doi={10.21437/Interspeech.2019-3207},
  url={http://dx.doi.org/10.21437/Interspeech.2019-3207}
}