A Trie-Structured Bayesian Model for Unsupervised Morphological Segmentation
This work addresses morphological segmentation for languages with scarce resources, but it is incremental as it builds on existing Bayesian and embedding-based approaches.
The paper tackles unsupervised morphological segmentation by introducing a trie-structured Bayesian model that incorporates prior information from neural word embeddings and letter successor variety counts. The model outperforms other unsupervised methods on Turkish and shows promising results on English and German for scarce resources.
In this paper, we introduce a trie-structured Bayesian model for unsupervised morphological segmentation. We adopt prior information from different sources in the model. We use neural word embeddings to discover words that are morphologically derived from each other and thereby that are semantically similar. We use letter successor variety counts obtained from tries that are built by neural word embeddings. Our results show that using different information sources such as neural word embeddings and letter successor variety as prior information improves morphological segmentation in a Bayesian model. Our model outperforms other unsupervised morphological segmentation models on Turkish and gives promising results on English and German for scarce resources.