@inproceedings{pierrejean-tanguy-2018-towards,
title = "Towards Qualitative Word Embeddings Evaluation: Measuring Neighbors Variation",
author = "Pierrejean, B{\'e}n{\'e}dicte and
Tanguy, Ludovic",
editor = "Cordeiro, Silvio Ricardo and
Oraby, Shereen and
Pavalanathan, Umashanthi and
Rim, Kyeongmin",
booktitle = "Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Student Research Workshop",
month = jun,
year = "2018",
address = "New Orleans, Louisiana, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N18-4005",
doi = "10.18653/v1/N18-4005",
pages = "32--39",
abstract = "We propose a method to study the variation lying between different word embeddings models trained with different parameters. We explore the variation between models trained with only one varying parameter by observing the distributional neighbors variation and show how changing only one parameter can have a massive impact on a given semantic space. We show that the variation is not affecting all words of the semantic space equally. Variation is influenced by parameters such as setting a parameter to its minimum or maximum value but it also depends on the corpus intrinsic features such as the frequency of a word. We identify semantic classes of words remaining stable across the models trained and specific words having high variation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pierrejean-tanguy-2018-towards">
<titleInfo>
<title>Towards Qualitative Word Embeddings Evaluation: Measuring Neighbors Variation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bénédicte</namePart>
<namePart type="family">Pierrejean</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ludovic</namePart>
<namePart type="family">Tanguy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Silvio</namePart>
<namePart type="given">Ricardo</namePart>
<namePart type="family">Cordeiro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shereen</namePart>
<namePart type="family">Oraby</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Umashanthi</namePart>
<namePart type="family">Pavalanathan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyeongmin</namePart>
<namePart type="family">Rim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">New Orleans, Louisiana, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose a method to study the variation lying between different word embeddings models trained with different parameters. We explore the variation between models trained with only one varying parameter by observing the distributional neighbors variation and show how changing only one parameter can have a massive impact on a given semantic space. We show that the variation is not affecting all words of the semantic space equally. Variation is influenced by parameters such as setting a parameter to its minimum or maximum value but it also depends on the corpus intrinsic features such as the frequency of a word. We identify semantic classes of words remaining stable across the models trained and specific words having high variation.</abstract>
<identifier type="citekey">pierrejean-tanguy-2018-towards</identifier>
<identifier type="doi">10.18653/v1/N18-4005</identifier>
<location>
<url>https://aclanthology.org/N18-4005</url>
</location>
<part>
<date>2018-06</date>
<extent unit="page">
<start>32</start>
<end>39</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Qualitative Word Embeddings Evaluation: Measuring Neighbors Variation
%A Pierrejean, Bénédicte
%A Tanguy, Ludovic
%Y Cordeiro, Silvio Ricardo
%Y Oraby, Shereen
%Y Pavalanathan, Umashanthi
%Y Rim, Kyeongmin
%S Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop
%D 2018
%8 June
%I Association for Computational Linguistics
%C New Orleans, Louisiana, USA
%F pierrejean-tanguy-2018-towards
%X We propose a method to study the variation lying between different word embeddings models trained with different parameters. We explore the variation between models trained with only one varying parameter by observing the distributional neighbors variation and show how changing only one parameter can have a massive impact on a given semantic space. We show that the variation is not affecting all words of the semantic space equally. Variation is influenced by parameters such as setting a parameter to its minimum or maximum value but it also depends on the corpus intrinsic features such as the frequency of a word. We identify semantic classes of words remaining stable across the models trained and specific words having high variation.
%R 10.18653/v1/N18-4005
%U https://aclanthology.org/N18-4005
%U https://doi.org/10.18653/v1/N18-4005
%P 32-39
Markdown (Informal)
[Towards Qualitative Word Embeddings Evaluation: Measuring Neighbors Variation](https://aclanthology.org/N18-4005) (Pierrejean & Tanguy, NAACL 2018)
ACL