Saved in:
Bibliographic Details
Main Authors: Liu, Dezhi, Zhang, Richong, Wang, Ziqiao
Format: Preprint
Published: 2020
Subjects:
Online Access:https://arxiv.org/abs/2009.04413
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912741113987072
author Liu, Dezhi
Zhang, Richong
Wang, Ziqiao
author_facet Liu, Dezhi
Zhang, Richong
Wang, Ziqiao
contents SkipGram word embedding models with negative sampling, or SGN in short, is an elegant family of word embedding models. In this paper, we formulate a framework for word embedding, referred to as Word-Context Classification (WCC), that generalizes SGN to a wide family of models. The framework, which uses some ``noise examples'', is justified through theoretical analysis. The impact of noise distribution on the learning of the WCC embedding models is studied experimentally, suggesting that the best noise distribution is, in fact, the data distribution, in terms of both the embedding performance and the speed of convergence during training. Along our way, we discover several novel embedding models that outperform existing WCC models.
format Preprint
id arxiv_https___arxiv_org_abs_2009_04413
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle On SkipGram Word Embedding Models with Negative Sampling: Unified Framework and Impact of Noise Distributions
Liu, Dezhi
Zhang, Richong
Wang, Ziqiao
Computation and Language
Machine Learning
SkipGram word embedding models with negative sampling, or SGN in short, is an elegant family of word embedding models. In this paper, we formulate a framework for word embedding, referred to as Word-Context Classification (WCC), that generalizes SGN to a wide family of models. The framework, which uses some ``noise examples'', is justified through theoretical analysis. The impact of noise distribution on the learning of the WCC embedding models is studied experimentally, suggesting that the best noise distribution is, in fact, the data distribution, in terms of both the embedding performance and the speed of convergence during training. Along our way, we discover several novel embedding models that outperform existing WCC models.
title On SkipGram Word Embedding Models with Negative Sampling: Unified Framework and Impact of Noise Distributions
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2009.04413