Contextualization of Morphological Inflection

Ekaterina Vylomova, Ryan Cotterell, Trevor Cohn, Timothy Baldwin, Jason Eisner
2019 Proceedings of the 2019 Conference of the North  
Critical to natural language generation is the production of correctly inflected text. In this paper, we isolate the task of predicting a fully inflected sentence from its partially lemmatized version. Unlike traditional morphological inflection or surface realization, our task input does not provide "gold" tags that specify what morphological features to realize on each lemmatized word; rather, such features must be inferred from sentential context. We develop a neural hybrid graphical model
more » ... d graphical model that explicitly reconstructs morphological features before predicting the inflected forms, and compare this to a system that directly predicts the inflected forms without relying on any morphological annotation. We experiment on several typologically diverse languages from the Universal Dependencies treebanks, showing the utility of incorporating linguisticallymotivated latent variables into NLP models.
doi:10.18653/v1/n19-1203 dblp:conf/naacl/VylomovaCCBE19 fatcat:psy3hsja3ne4xbbow67gyewgou