Inflection Generation as Discriminative String Transduction

We approach the task of morphological inflection generation as discriminative string transduction. Our supervised system learns to generate word-forms from lemmas accompanied by morphological tags, and refines them by referring to the other forms within a paradigm. Results of experiments on six diverse languages with varying amounts of training data demonstrate that our approach improves the state of the art in terms of predicting inflected word-forms.

Acknowledgments

We thank Mans Hulden and Aki-Juhani Kyrol¨ ainen ¨ for their assistance in analyzing Finnish errors.. This research was supported by the Natural Sciences and Engineering Research Council of Canada, and the Alberta Innovates Technology Futures.