# Unsupervised Learning of Morphological Forests

arXiv: https://arxiv.org/abs/1702.07015 · HTML: https://mlsanity.com/paper/1702.07015/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Feb 2017.

## Built on by (most cited first, 2 of 2)

- [Inducing Meaningful Units from Character Sequences with Dynamic Capacity Slot Attention](https://mlsanity.com/paper/2102.01223/) (2021)
- [The Minimum Edit Arborescence Problem and Its Use in Compressing Graph Collections [Extended Version]](https://mlsanity.com/paper/2107.14525/) (2021)

## Abstract (arXiv)

This paper focuses on unsupervised modeling of morphological families, collectively comprising a forest over the language vocabulary. This formulation enables us to capture edgewise properties reflecting single-step morphological derivations, along with global distributional properties of the entire forest. These global properties constrain the size of the affix set and encourage formation of tight morphological families. The resulting objective is solved using Integer Linear Programming (ILP) paired with contrastive estimation. We train the model by alternating between optimizing the local log-linear model and the global ILP objective. We evaluate our system on three tasks: root detection, clustering of morphological families and segmentation. Our experiments demonstrate that our model yields consistent gains in all three tasks compared with the best published results.