Mittens: an Extension of GloVe for Learning Domain-Specialized Representations

Nicholas Dingwall, Christopher Potts


Abstract
We present a simple extension of the GloVe representation learning model that begins with general-purpose representations and updates them based on data from a specialized domain. We show that the resulting representations can lead to faster learning and better results on a variety of tasks.
Anthology ID:
N18-2034
Volume:
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Editors:
Marilyn Walker, Heng Ji, Amanda Stent
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
212–217
Language:
URL:
https://aclanthology.org/N18-2034
DOI:
10.18653/v1/N18-2034
Bibkey:
Cite (ACL):
Nicholas Dingwall and Christopher Potts. 2018. Mittens: an Extension of GloVe for Learning Domain-Specialized Representations. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 212–217, New Orleans, Louisiana. Association for Computational Linguistics.
Cite (Informal):
Mittens: an Extension of GloVe for Learning Domain-Specialized Representations (Dingwall & Potts, NAACL 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/N18-2034.pdf
Software:
 N18-2034.Software.zip
Code
 roamanalytics/mittens
Data
IMDb Movie Reviews