Explaining Character-Aware Neural Networks for Word-Level Prediction: Do They Discover Linguistic Rules?

Fréderic Godin, Kris Demuynck, Joni Dambre, Wesley De Neve, Thomas Demeester


Abstract
Character-level features are currently used in different neural network-based natural language processing algorithms. However, little is known about the character-level patterns those models learn. Moreover, models are often compared only quantitatively while a qualitative analysis is missing. In this paper, we investigate which character-level patterns neural networks learn and if those patterns coincide with manually-defined word segmentations and annotations. To that end, we extend the contextual decomposition technique (Murdoch et al. 2018) to convolutional neural networks which allows us to compare convolutional neural networks and bidirectional long short-term memory networks. We evaluate and compare these models for the task of morphological tagging on three morphologically different languages and show that these models implicitly discover understandable linguistic rules.
Anthology ID:
D18-1365
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
3275–3284
Language:
URL:
https://www.aclweb.org/anthology/D18-1365
DOI:
10.18653/v1/D18-1365
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D18-1365.pdf
Attachment:
 D18-1365.Attachment.zip
Video:
 https://vimeo.com/305681577