Data Augmentation for Context-Sensitive Neural Lemmatization Using Inflection Tables and Raw Text

Toms Bergmanis, Sharon Goldwater


Abstract
Lemmatization aims to reduce the sparse data problem by relating the inflected forms of a word to its dictionary form. Using context can help, both for unseen and ambiguous words. Yet most context-sensitive approaches require full lemma-annotated sentences for training, which may be scarce or unavailable in low-resource languages. In addition (as shown here), in a low-resource setting, a lemmatizer can learn more from n labeled examples of distinct words (types) than from n (contiguous) labeled tokens, since the latter contain far fewer distinct types. To combine the efficiency of type-based learning with the benefits of context, we propose a way to train a context-sensitive lemmatizer with little or no labeled corpus data, using inflection tables from the UniMorph project and raw text examples from Wikipedia that provide sentence contexts for the unambiguous UniMorph examples. Despite these being unambiguous examples, the model successfully generalizes from them, leading to improved results (both overall, and especially on unseen words) in comparison to a baseline that does not use context.
Anthology ID:
N19-1418
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Jill Burstein, Christy Doran, Thamar Solorio
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4119–4128
Language:
URL:
https://aclanthology.org/N19-1418
DOI:
10.18653/v1/N19-1418
Bibkey:
Cite (ACL):
Toms Bergmanis and Sharon Goldwater. 2019. Data Augmentation for Context-Sensitive Neural Lemmatization Using Inflection Tables and Raw Text. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4119–4128, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Data Augmentation for Context-Sensitive Neural Lemmatization Using Inflection Tables and Raw Text (Bergmanis & Goldwater, NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/N19-1418.pdf
Presentation:
 N19-1418.Presentation.pdf
Video:
 https://vimeo.com/361822826
Code
 tomsbergmanis/data_augumentation_um_wiki