Feature Hashing for Language and Dialect Identification

Shervin Malmasi, Mark Dras


Abstract
We evaluate feature hashing for language identification (LID), a method not previously used for this task. Using a standard dataset, we first show that while feature performance is high, LID data is highly dimensional and mostly sparse (>99.5%) as it includes large vocabularies for many languages; memory requirements grow as languages are added. Next we apply hashing using various hash sizes, demonstrating that there is no performance loss with dimensionality reductions of up to 86%. We also show that using an ensemble of low-dimension hash-based classifiers further boosts performance. Feature hashing is highly useful for LID and holds great promise for future work in this area.
Anthology ID:
P17-2063
Volume:
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
July
Year:
2017
Address:
Vancouver, Canada
Editors:
Regina Barzilay, Min-Yen Kan
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
399–403
Language:
URL:
https://aclanthology.org/P17-2063
DOI:
10.18653/v1/P17-2063
Bibkey:
Cite (ACL):
Shervin Malmasi and Mark Dras. 2017. Feature Hashing for Language and Dialect Identification. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 399–403, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
Feature Hashing for Language and Dialect Identification (Malmasi & Dras, ACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/P17-2063.pdf