DeepAI AI Chat
Log In Sign Up

Unsupervised Learning of Morphological Forests

by   Jiaming Luo, et al.

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.


Building Morphological Chains for Agglutinative Languages

In this paper, we build morphological chains for agglutinative languages...

An Unsupervised Method for Uncovering Morphological Chains

Most state-of-the-art systems today produce morphological analysis based...

Subword Segmental Language Modelling for Nguni Languages

Subwords have become the standard units of text in NLP, enabling efficie...

Morphological Segmentation Inside-Out

Morphological segmentation has traditionally been modeled with non-hiera...

Morphological Analyzer and Generator for Russian and Ukrainian Languages

pymorphy2 is a morphological analyzer and generator for Russian and Ukra...