Character-based recurrent neural networks for morphological relational reasoning

Olof Mogren, Richard Johansson


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.
Anthology ID:
W17-4108
Volume:
Proceedings of the First Workshop on Subword and Character Level Models in NLP
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Editors:
Manaal Faruqui, Hinrich Schuetze, Isabel Trancoso, Yadollah Yaghoobzadeh
Venue:
SCLeM
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
57–63
Language:
URL:
https://aclanthology.org/W17-4108
DOI:
10.18653/v1/W17-4108
Bibkey:
Cite (ACL):
Olof Mogren and Richard Johansson. 2017. Character-based recurrent neural networks for morphological relational reasoning. In Proceedings of the First Workshop on Subword and Character Level Models in NLP, pages 57–63, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Character-based recurrent neural networks for morphological relational reasoning (Mogren & Johansson, SCLeM 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/W17-4108.pdf