# Neural Multi-Source Morphological Reinflection

arXiv: https://arxiv.org/abs/1612.06027 · HTML: https://mlsanity.com/paper/1612.06027/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Dec 2016.

## Built on by (most cited first, 7 of 7)

- [Counting the Bugs in ChatGPT's Wugs: A Multilingual Investigation into the Morphological Capabilities of a Large Language Model](https://mlsanity.com/paper/2310.15113/) (2023)
- [Frequency matters: Modeling irregular morphological patterns in Spanish with Transformers](https://mlsanity.com/paper/2410.21013/) (2024)
- [Morphological Processing of Low-Resource Languages: Where We Are and What's Next](https://mlsanity.com/paper/2203.08909/) (2022)
- [Computational Morphology with Neural Network Approaches](https://mlsanity.com/paper/2105.09404/) (2021)
- [Character-aware Transformers Learn an Irregular Morphological Pattern Yet None Generalize Like Humans](https://mlsanity.com/paper/2602.14100/) (2026)
- [Zero-Shot Morphological Discovery in Low-Resource Bantu Languages via Cross-Lingual Transfer and Unsupervised Clustering](https://mlsanity.com/paper/2604.22723/) (2026)
- [Probing Character-level Transformers for the Spanish L-shaped Morphome](https://mlsanity.com/paper/2608.03452/) (2026)

## Abstract (arXiv)

We explore the task of multi-source morphological reinflection, which generalizes the standard, single-source version. The input consists of (i) a target tag and (ii) multiple pairs of source form and source tag for a lemma. The motivation is that it is beneficial to have access to more than one source form since different source forms can provide complementary information, e.g., different stems. We further present a novel extension to the encoder- decoder recurrent neural architecture, consisting of multiple encoders, to better solve the task. We show that our new architecture outperforms single-source reinflection models and publish our dataset for multi-source morphological reinflection to facilitate future research.