# Neural Transductive Learning and Beyond: Morphological Generation in the Minimal-Resource Setting

arXiv: https://arxiv.org/abs/1809.08733 · HTML: https://mlsanity.com/paper/1809.08733/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Sep 2018.

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

- [Morphological Processing of Low-Resource Languages: Where We Are and What's Next](https://mlsanity.com/paper/2203.08909/) (2022)
- [Interdisciplinary Research in Conversation: A Case Study in Computational Morphology for Language Documentation](https://mlsanity.com/paper/2509.10644/) (2025)
- [Computational Morphology with Neural Network Approaches](https://mlsanity.com/paper/2105.09404/) (2021)
- [Transductive Learning for Abstractive News Summarization](https://mlsanity.com/paper/2104.09500/) (2021)
- [CommonMorph: Participatory Morphological Documentation Platform](https://mlsanity.com/paper/2604.04515/) (2026)

## Abstract (arXiv)

Neural state-of-the-art sequence-to-sequence (seq2seq) models often do not perform well for small training sets. We address paradigm completion, the morphological task of, given a partial paradigm, generating all missing forms. We propose two new methods for the minimal-resource setting: (i) Paradigm transduction: Since we assume only few paradigms available for training, neural seq2seq models are able to capture relationships between paradigm cells, but are tied to the idiosyncracies of the training set. Paradigm transduction mitigates this problem by exploiting the input subset of inflected forms at test time. (ii) Source selection with high precision (SHIP): Multi-source models which learn to automatically select one or multiple sources to predict a target inflection do not perform well in the minimal-resource setting. SHIP is an alternative to identify a reliable source if training data is limited. On a 52-language benchmark dataset, we outperform the previous state of the art by up to 9.71% absolute accuracy.