A Trie-structured Bayesian Model for Unsupervised Morphological Segmentation

Creative Commons License

Kurfali M., Ustun A., CAN BUĞLALILAR B.

18th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing), Budapest, Hungary, 17 - 23 April 2017, vol.10761, pp.87-98 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 10761
  • Doi Number: 10.1007/978-3-319-77113-7_7
  • City: Budapest
  • Country: Hungary
  • Page Numbers: pp.87-98
  • Middle East Technical University Affiliated: Yes


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.