Incremental Skip-gram Model with Negative Sampling

Nobuhiro Kaji, Hayato Kobayashi


Abstract
This paper explores an incremental training strategy for the skip-gram model with negative sampling (SGNS) from both empirical and theoretical perspectives. Existing methods of neural word embeddings, including SGNS, are multi-pass algorithms and thus cannot perform incremental model update. To address this problem, we present a simple incremental extension of SGNS and provide a thorough theoretical analysis to demonstrate its validity. Empirical experiments demonstrated the correctness of the theoretical analysis as well as the practical usefulness of the incremental algorithm.
Anthology ID:
D17-1037
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
363–371
Language:
URL:
https://www.aclweb.org/anthology/D17-1037
DOI:
10.18653/v1/D17-1037
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D17-1037.pdf
Attachment:
 D17-1037.Attachment.pdf
Poster:
 D17-1037.Poster.pdf