Incorporating Subword Information into Matrix Factorization Word Embeddings

Alexandre Salle, Aline Villavicencio


Abstract
The positive effect of adding subword information to word embeddings has been demonstrated for predictive models. In this paper we investigate whether similar benefits can also be derived from incorporating subwords into counting models. We evaluate the impact of different types of subwords (n-grams and unsupervised morphemes), with results confirming the importance of subword information in learning representations of rare and out-of-vocabulary words.
Anthology ID:
W18-1209
Volume:
Proceedings of the Second Workshop on Subword/Character LEvel Models
Month:
June
Year:
2018
Address:
New Orleans
Venues:
NAACL | SCLeM | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
66–71
Language:
URL:
https://aclanthology.org/W18-1209
DOI:
10.18653/v1/W18-1209
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/W18-1209.pdf
Video:
 https://vimeo.com/291466308
Code
 alexandres/lexvec