arxivst stuff from arxiv that you should probably bookmark

Incremental Skip-gram Model with Negative Sampling

Abstract · Apr 13, 2017 00:36 ·

training word 2013b sgns validity incremental mikolov embeddings theoretical cs-cl

Arxiv Abstract

  • Nobuhiro Kaji
  • Hayato Kobayashi

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.

Read the paper (pdf) »