BibTeX

@inProceedings{Mogren-Olof2017-256929,
	title        = {Character-based Recurrent Neural Networks for Morphological Relational Reasoning},
	abstract     = {We present a model for predicting word forms based on
	    morphological relational reasoning with analogies. While
	    previous work has explored tasks such as morphological inflection
	    and reinflection, these models rely on an explicit enumeration
	    of morphological features, which may not be available in all cases.
	    
	    To address the task of predicting a word form given a demo
	      relation (a pair of word forms) and a query word, we
	    devise a character-based recurrent neural network architecture
	    using three separate encoders and a decoder.
	    
	    We also investigate a multiclass learning setup, where the
	    prediction of the relation type label is used as an auxiliary task.
	    Our results show that the exact form can be predicted for
	    English with an accuracy of 94.7%. For Swedish, which has a more
	    complex morphology with more inflectional patterns for nouns and
	    verbs, the accuracy is 89.3%. We also show that using the
	    auxiliary task of learning the relation type speeds up convergence
	    and improves the prediction accuracy for the word generation task.},
	booktitle    = {Proceedings of the First Workshop on Subword and Character Level Models in NLP},
	author       = {Mogren, Olof and Johansson, Richard},
	year         = {2017},
	publisher    = {Association for Computational Linguistics},
	address      = {Stroudsburg, PA, United States},
}