Explaining Character-Aware Neural Networks for Word-Level Prediction: Do They Discover Linguistic Rules?
This work addresses the interpretability gap in NLP models for researchers and practitioners, though it is incremental as it extends existing techniques.
The paper investigates whether character-aware neural networks learn interpretable linguistic rules for morphological tagging, finding that these models implicitly discover understandable patterns across three languages.
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. Our implementation can be found at https://github.com/FredericGodin/ContextualDecomposition-NLP .