@inproceedings{yenicelik-etal-2020-bert,
title = "How does {BERT} capture semantics? A closer look at polysemous words",
author = "Yenicelik, David and
Schmidt, Florian and
Kilcher, Yannic",
editor = "Alishahi, Afra and
Belinkov, Yonatan and
Chrupa{\l}a, Grzegorz and
Hupkes, Dieuwke and
Pinter, Yuval and
Sajjad, Hassan",
booktitle = "Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.blackboxnlp-1.15",
doi = "10.18653/v1/2020.blackboxnlp-1.15",
pages = "156--162",
abstract = "The recent paradigm shift to contextual word embeddings has seen tremendous success across a wide range of down-stream tasks. However, little is known on how the emergent relation of context and semantics manifests geometrically. We investigate polysemous words as one particularly prominent instance of semantic organization. Our rigorous quantitative analysis of linear separability and cluster organization in embedding vectors produced by BERT shows that semantics do not surface as isolated clusters but form seamless structures, tightly coupled with sentiment and syntax.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yenicelik-etal-2020-bert">
<titleInfo>
<title>How does BERT capture semantics? A closer look at polysemous words</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Yenicelik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Florian</namePart>
<namePart type="family">Schmidt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yannic</namePart>
<namePart type="family">Kilcher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Afra</namePart>
<namePart type="family">Alishahi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yonatan</namePart>
<namePart type="family">Belinkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Grzegorz</namePart>
<namePart type="family">Chrupała</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dieuwke</namePart>
<namePart type="family">Hupkes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuval</namePart>
<namePart type="family">Pinter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hassan</namePart>
<namePart type="family">Sajjad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The recent paradigm shift to contextual word embeddings has seen tremendous success across a wide range of down-stream tasks. However, little is known on how the emergent relation of context and semantics manifests geometrically. We investigate polysemous words as one particularly prominent instance of semantic organization. Our rigorous quantitative analysis of linear separability and cluster organization in embedding vectors produced by BERT shows that semantics do not surface as isolated clusters but form seamless structures, tightly coupled with sentiment and syntax.</abstract>
<identifier type="citekey">yenicelik-etal-2020-bert</identifier>
<identifier type="doi">10.18653/v1/2020.blackboxnlp-1.15</identifier>
<location>
<url>https://aclanthology.org/2020.blackboxnlp-1.15</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>156</start>
<end>162</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How does BERT capture semantics? A closer look at polysemous words
%A Yenicelik, David
%A Schmidt, Florian
%A Kilcher, Yannic
%Y Alishahi, Afra
%Y Belinkov, Yonatan
%Y Chrupała, Grzegorz
%Y Hupkes, Dieuwke
%Y Pinter, Yuval
%Y Sajjad, Hassan
%S Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F yenicelik-etal-2020-bert
%X The recent paradigm shift to contextual word embeddings has seen tremendous success across a wide range of down-stream tasks. However, little is known on how the emergent relation of context and semantics manifests geometrically. We investigate polysemous words as one particularly prominent instance of semantic organization. Our rigorous quantitative analysis of linear separability and cluster organization in embedding vectors produced by BERT shows that semantics do not surface as isolated clusters but form seamless structures, tightly coupled with sentiment and syntax.
%R 10.18653/v1/2020.blackboxnlp-1.15
%U https://aclanthology.org/2020.blackboxnlp-1.15
%U https://doi.org/10.18653/v1/2020.blackboxnlp-1.15
%P 156-162
Markdown (Informal)
[How does BERT capture semantics? A closer look at polysemous words](https://aclanthology.org/2020.blackboxnlp-1.15) (Yenicelik et al., BlackboxNLP 2020)
ACL