# Neural Induction of Finite-State Transducers

arXiv: https://arxiv.org/abs/2601.10918 · HTML: https://mlsanity.com/paper/2601.10918/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 59 references that are in the map.
- First posted on arXiv 16 Jan 2026.

## Builds on (most cited first, 11 of 11)

- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization](https://mlsanity.com/paper/1603.06560/) (2016)
- [Theoretical Limitations of Self-Attention in Neural Sequence Models](https://mlsanity.com/paper/1906.06755/) (2019)
- [On the Practical Computational Power of Finite Precision RNNs for Language Recognition](https://mlsanity.com/paper/1805.04908/) (2018)
- [Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples](https://mlsanity.com/paper/1711.09576/) (2017)
- [SIGMORPHON 2020 Shared Task 0: Typologically Diverse Morphological Inflection](https://mlsanity.com/paper/2006.11572/) (2020)
- [A Large-Scale Comparison of Historical Text Normalization Systems](https://mlsanity.com/paper/1904.02036/) (2019)
- [Towards Realistic Practices In Low-Resource Natural Language Processing: The Development Set](https://mlsanity.com/paper/1909.01522/) (2019)
- [Learning with Interpretable Structure from Gated RNN](https://mlsanity.com/paper/1810.10708/) (2018)
- [Mobile Keyboard Input Decoding with Finite-State Transducers](https://mlsanity.com/paper/1704.03987/) (2017)
- [A Comparative Study of Rule Extraction for Recurrent Neural Networks](https://mlsanity.com/paper/1801.05420/) (2018)

## Abstract (arXiv)

Finite-State Transducers (FSTs) are effective models for string-to-string rewriting tasks, often providing the efficiency necessary for high-performance applications, but constructing transducers by hand is difficult. In this work, we propose a novel method for automatically constructing unweighted FSTs following the hidden state geometry learned by a recurrent neural network. We evaluate our methods on real-world datasets for morphological inflection, grapheme-to-phoneme prediction, and historical normalization, showing that the constructed FSTs are highly accurate and robust for many datasets, substantially outperforming classical transducer learning algorithms by up to 87% accuracy on held-out test sets.