Improving morphology induction by learning spelling rules

Sharon Goldwater, Jason Naradowski

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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.
Original languageEnglish
Title of host publicationProceedings of the 21st International Joint Conference on Artificial Intelligence (IJCAI-09)
Pages1-6
Number of pages6
Publication statusPublished - 2009
EventInternational Joint Conference on Artificial Intelligence - California, Pasedena, United States
Duration: 11 Jul 2009 → …

Conference

ConferenceInternational Joint Conference on Artificial Intelligence
Country/TerritoryUnited States
CityPasedena
Period11/07/09 → …

Fingerprint

Dive into the research topics of 'Improving morphology induction by learning spelling rules'. Together they form a unique fingerprint.

Cite this