Unsupervised learning of morphology is an important task for human learners and in natural language processing systems. Previous systems focus on segmenting words into substrings (taking ⇒ tak.ing), but sometimes a segmentation-only analysis is insufficient (e.g., taking may be more appropriately analyzed as take+ing, with a spelling rule accounting for the deletion of the stem-final e). In this paper, we develop a Bayesian model for simultaneously inducing both morphology and spelling rules. We show that the addition of spelling rules improves performance over the baseline morphology-only model.
|Title of host publication||Proceedings of the 21st International Joint Conference on Artificial Intelligence (IJCAI-09)|
|Number of pages||6|
|Publication status||Published - 2009|
|Event||International Joint Conference on Artificial Intelligence - California, Pasedena, United States|
Duration: 11 Jul 2009 → …
|Conference||International Joint Conference on Artificial Intelligence|
|Period||11/07/09 → …|