Improving Morphology Induction by Learning Spelling Rules
Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence. Pages 1531-1535.
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.Jason Naradowsky, Sharon Goldwater
@inproceedings{ijcai2009p256,
title = {Improving Morphology Induction by Learning Spelling Rules},
author = {Naradowsky, Jason and Goldwater, Sharon},
booktitle = {Proceedings of the Twenty-First International Joint Conference on
Artificial Intelligence, {IJCAI-09}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Hiroaki Kitano},
pages = {1531--1535},
year = {2009},
url = {https://ijcai.org/proceedings/2009/256},
}
TY - CPAPER TI - Improving Morphology Induction by Learning Spelling Rules AU - Naradowsky, Jason AU - Goldwater, Sharon T2 - Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence, IJCAI-09 PB - International Joint Conferences on Artificial Intelligence PY - 2009 SP - 1531 EP - 1535 UR - https://ijcai.org/proceedings/2009/256 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
