@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},
}