Better Character Language Modeling through Morphology

Terra Blevins, Luke Zettlemoyer


Abstract
We incorporate morphological supervision into character language models (CLMs) via multitasking and show that this addition improves bits-per-character (BPC) performance across 24 languages, even when the morphology data and language modeling data are disjoint. Analyzing the CLMs shows that inflected words benefit more from explicitly modeling morphology than uninflected words, and that morphological supervision improves performance even as the amount of language modeling data grows. We then transfer morphological supervision across languages to improve performance in the low-resource setting.
Anthology ID:
P19-1156
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Anna Korhonen, David Traum, Lluís Màrquez
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1606–1613
Language:
URL:
https://aclanthology.org/P19-1156
DOI:
10.18653/v1/P19-1156
Bibkey:
Cite (ACL):
Terra Blevins and Luke Zettlemoyer. 2019. Better Character Language Modeling through Morphology. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1606–1613, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Better Character Language Modeling through Morphology (Blevins & Zettlemoyer, ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1156.pdf