Effective search space reduction for spell correction using character neural embeddings

Harshit Pande


Abstract
We present a novel, unsupervised, and distance measure agnostic method for search space reduction in spell correction using neural character embeddings. The embeddings are learned by skip-gram word2vec training on sequences generated from dictionary words in a phonetic information-retentive manner. We report a very high performance in terms of both success rates and reduction of search space on the Birkbeck spelling error corpus. To the best of our knowledge, this is the first application of word2vec to spell correction.
Anthology ID:
E17-2027
Volume:
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
Month:
April
Year:
2017
Address:
Valencia, Spain
Editors:
Mirella Lapata, Phil Blunsom, Alexander Koller
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
170–174
Language:
URL:
https://aclanthology.org/E17-2027
DOI:
Bibkey:
Cite (ACL):
Harshit Pande. 2017. Effective search space reduction for spell correction using character neural embeddings. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 170–174, Valencia, Spain. Association for Computational Linguistics.
Cite (Informal):
Effective search space reduction for spell correction using character neural embeddings (Pande, EACL 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/E17-2027.pdf