A Trie-Structured Bayesian Model for Unsupervised Morphological Segmentation
| Autor: | Kurfalı, Murathan, Üstün, Ahmet, Can, Burcu |
|---|---|
| Rok vydání: | 2017 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | 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. Comment: 12 pages, accepted and presented at the CICLING 2017 - 18th International Conference on Intelligent Text Processing and Computational Linguistics |
| Databáze: | arXiv |
| Externí odkaz: |
|