Contextualization of Morphological Inflection
This addresses a key challenge in natural language generation for linguists and NLP practitioners, but it is incremental as it builds on existing morphological inflection tasks.
The paper tackles the problem of predicting fully inflected sentences from partially lemmatized text without gold morphological tags, requiring inference from context. It develops a neural hybrid graphical model that reconstructs morphological features before inflection, showing utility across diverse languages from Universal Dependencies treebanks.
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.