Misspelling Oblivious Word Embeddings

Aleksandra Piktus, Necati Bora Edizel, Piotr Bojanowski, Edouard Grave, Rui Ferreira, Fabrizio Silvestri


Abstract
In this paper we present a method to learn word embeddings that are resilient to misspellings. Existing word embeddings have limited applicability to malformed texts, which contain a non-negligible amount of out-of-vocabulary words. We propose a method combining FastText with subwords and a supervised task of learning misspelling patterns. In our method, misspellings of each word are embedded close to their correct variants. We train these embeddings on a new dataset we are releasing publicly. Finally, we experimentally show the advantages of this approach on both intrinsic and extrinsic NLP tasks using public test sets.
Anthology ID:
N19-1326
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:
3226–3234
Language:
URL:
https://aclanthology.org/N19-1326
DOI:
10.18653/v1/N19-1326
Bibkey:
Cite (ACL):
Aleksandra Piktus, Necati Bora Edizel, Piotr Bojanowski, Edouard Grave, Rui Ferreira, and Fabrizio Silvestri. 2019. Misspelling Oblivious Word Embeddings. 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 3226–3234, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Misspelling Oblivious Word Embeddings (Piktus et al., NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/N19-1326.pdf
Code
 bedizel/moe +  additional community code