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

arXiv: https://arxiv.org/abs/1808.09551 · HTML: https://mlsanity.com/paper/1808.09551/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Aug 2018.

## Built on by (most cited first, 5 of 5)

- [Neuron-level Interpretation of Deep NLP Models: A Survey](https://mlsanity.com/paper/2108.13138/) (2021)
- [ZARA: Improving Few-Shot Self-Rationalization for Small Language Models](https://mlsanity.com/paper/2305.07355/) (2023)
- [INTERACTION: A Generative XAI Framework for Natural Language Inference Explanations](https://mlsanity.com/paper/2209.01061/) (2022)
- [chDzDT: Word-level morphology-aware language model for Algerian social media text](https://mlsanity.com/paper/2509.01772/) (2025)
- [CIDR: A Cooperative Integrated Dynamic Refining Method for Minimal Feature Removal Problem](https://mlsanity.com/paper/2312.08157/) (2023)

## Abstract (arXiv)

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 .