Contextualization of Morphological Inflection

Ekaterina Vylomova, Ryan Cotterell, Trevor Cohn, Timothy Baldwin, Jason Eisner


Abstract
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 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 linguistically-motivated latent variables into NLP models.
Anthology ID:
N19-1203
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2018–2024
Language:
URL:
https://www.aclweb.org/anthology/N19-1203
DOI:
10.18653/v1/N19-1203
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/N19-1203.pdf
Video:
 https://vimeo.com/354264026