Ensembles of Neural Morphological Inflection Models

Ilmari Kylliäinen, Miikka Silfverberg


Abstract
We investigate different ensemble learning techniques for neural morphological inflection using bidirectional LSTM encoder-decoder models with attention. We experiment with weighted and unweighted majority voting and bagging. We find that all investigated ensemble methods lead to improved accuracy over a baseline of a single model. However, contrary to expectation based on earlier work by Najafi et al. (2018) and Silfverberg et al. (2017), weighting does not deliver clear benefits. Bagging was found to underperform plain voting ensembles in general.
Anthology ID:
W19-6132
Volume:
Proceedings of the 22nd Nordic Conference on Computational Linguistics
Month:
September–October
Year:
2019
Address:
Turku, Finland
Editors:
Mareike Hartmann, Barbara Plank
Venue:
NoDaLiDa
SIG:
Publisher:
Linköping University Electronic Press
Note:
Pages:
304–309
Language:
URL:
https://aclanthology.org/W19-6132
DOI:
Bibkey:
Cite (ACL):
Ilmari Kylliäinen and Miikka Silfverberg. 2019. Ensembles of Neural Morphological Inflection Models. In Proceedings of the 22nd Nordic Conference on Computational Linguistics, pages 304–309, Turku, Finland. Linköping University Electronic Press.
Cite (Informal):
Ensembles of Neural Morphological Inflection Models (Kylliäinen & Silfverberg, NoDaLiDa 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-6132.pdf