Derivational morphology is a fundamental and complex characteristic of language. In this paper we propose the new task of predicting the derivational form of a given base-form lemma that is appropriate for a given context. We present an encoder- decoder style neural network to produce a derived form character-by-character, based on its corresponding character-level representation of the base form and the context. We demonstrate that our model is able to generate valid context-sensitive derivations from known base forms, but is less accurate under a lexicon agnostic setting.
CITATION STYLE
Vylomova, E., Cotterell, R., Baldwin, T., & Cohn, T. (2017). Context-aware prediction of derivational word-forms. In 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Proceedings of Conference (Vol. 2, pp. 118–124). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/e17-2019
Mendeley helps you to discover research relevant for your work.