@inproceedings{zhang-zweigenbaum-2018-gneg,
title = "{GNEG}: Graph-Based Negative Sampling for word2vec",
author = "Zhang, Zheng and
Zweigenbaum, Pierre",
editor = "Gurevych, Iryna and
Miyao, Yusuke",
booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P18-2090",
doi = "10.18653/v1/P18-2090",
pages = "566--571",
abstract = "Negative sampling is an important component in word2vec for distributed word representation learning. We hypothesize that taking into account global, corpus-level information and generating a different noise distribution for each target word better satisfies the requirements of negative examples for each training word than the original frequency-based distribution. In this purpose we pre-compute word co-occurrence statistics from the corpus and apply to it network algorithms such as random walk. We test this hypothesis through a set of experiments whose results show that our approach boosts the word analogy task by about 5{\%} and improves the performance on word similarity tasks by about 1{\%} compared to the skip-gram negative sampling baseline.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-zweigenbaum-2018-gneg">
<titleInfo>
<title>GNEG: Graph-Based Negative Sampling for word2vec</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Zweigenbaum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Miyao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Negative sampling is an important component in word2vec for distributed word representation learning. We hypothesize that taking into account global, corpus-level information and generating a different noise distribution for each target word better satisfies the requirements of negative examples for each training word than the original frequency-based distribution. In this purpose we pre-compute word co-occurrence statistics from the corpus and apply to it network algorithms such as random walk. We test this hypothesis through a set of experiments whose results show that our approach boosts the word analogy task by about 5% and improves the performance on word similarity tasks by about 1% compared to the skip-gram negative sampling baseline.</abstract>
<identifier type="citekey">zhang-zweigenbaum-2018-gneg</identifier>
<identifier type="doi">10.18653/v1/P18-2090</identifier>
<location>
<url>https://aclanthology.org/P18-2090</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>566</start>
<end>571</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GNEG: Graph-Based Negative Sampling for word2vec
%A Zhang, Zheng
%A Zweigenbaum, Pierre
%Y Gurevych, Iryna
%Y Miyao, Yusuke
%S Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F zhang-zweigenbaum-2018-gneg
%X Negative sampling is an important component in word2vec for distributed word representation learning. We hypothesize that taking into account global, corpus-level information and generating a different noise distribution for each target word better satisfies the requirements of negative examples for each training word than the original frequency-based distribution. In this purpose we pre-compute word co-occurrence statistics from the corpus and apply to it network algorithms such as random walk. We test this hypothesis through a set of experiments whose results show that our approach boosts the word analogy task by about 5% and improves the performance on word similarity tasks by about 1% compared to the skip-gram negative sampling baseline.
%R 10.18653/v1/P18-2090
%U https://aclanthology.org/P18-2090
%U https://doi.org/10.18653/v1/P18-2090
%P 566-571
Markdown (Informal)
[GNEG: Graph-Based Negative Sampling for word2vec](https://aclanthology.org/P18-2090) (Zhang & Zweigenbaum, ACL 2018)
ACL
- Zheng Zhang and Pierre Zweigenbaum. 2018. GNEG: Graph-Based Negative Sampling for word2vec. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 566–571, Melbourne, Australia. Association for Computational Linguistics.