@inproceedings{turton-etal-2021-deriving,
title = "Deriving Contextualised Semantic Features from {BERT} (and Other Transformer Model) Embeddings",
author = "Turton, Jacob and
Smith, Robert Elliott and
Vinson, David",
editor = "Rogers, Anna and
Calixto, Iacer and
Vuli{\'c}, Ivan and
Saphra, Naomi and
Kassner, Nora and
Camburu, Oana-Maria and
Bansal, Trapit and
Shwartz, Vered",
booktitle = "Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.repl4nlp-1.26",
doi = "10.18653/v1/2021.repl4nlp-1.26",
pages = "248--262",
abstract = "Models based on the transformer architecture, such as BERT, have marked a crucial step forward in the field of Natural Language Processing. Importantly, they allow the creation of word embeddings that capture important semantic information about words in context. However, as single entities, these embeddings are difficult to interpret and the models used to create them have been described as opaque. Binder and colleagues proposed an intuitive embedding space where each dimension is based on one of 65 core semantic features. Unfortunately, the space only exists for a small data-set of 535 words, limiting its uses. Previous work (Utsumi, 2018, 2020; Turton et al., 2020) has shown that Binder features can be derived from static embeddings and successfully extrapolated to a large new vocabulary. Taking the next step, this paper demonstrates that Binder features can be derived from the BERT embedding space. This provides two things; (1) semantic feature values derived from contextualised word embeddings and (2) insights into how semantic features are represented across the different layers of the BERT model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="turton-etal-2021-deriving">
<titleInfo>
<title>Deriving Contextualised Semantic Features from BERT (and Other Transformer Model) Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jacob</namePart>
<namePart type="family">Turton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="given">Elliott</namePart>
<namePart type="family">Smith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Vinson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iacer</namePart>
<namePart type="family">Calixto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Vulić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naomi</namePart>
<namePart type="family">Saphra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nora</namePart>
<namePart type="family">Kassner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oana-Maria</namePart>
<namePart type="family">Camburu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trapit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vered</namePart>
<namePart type="family">Shwartz</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>Models based on the transformer architecture, such as BERT, have marked a crucial step forward in the field of Natural Language Processing. Importantly, they allow the creation of word embeddings that capture important semantic information about words in context. However, as single entities, these embeddings are difficult to interpret and the models used to create them have been described as opaque. Binder and colleagues proposed an intuitive embedding space where each dimension is based on one of 65 core semantic features. Unfortunately, the space only exists for a small data-set of 535 words, limiting its uses. Previous work (Utsumi, 2018, 2020; Turton et al., 2020) has shown that Binder features can be derived from static embeddings and successfully extrapolated to a large new vocabulary. Taking the next step, this paper demonstrates that Binder features can be derived from the BERT embedding space. This provides two things; (1) semantic feature values derived from contextualised word embeddings and (2) insights into how semantic features are represented across the different layers of the BERT model.</abstract>
<identifier type="citekey">turton-etal-2021-deriving</identifier>
<identifier type="doi">10.18653/v1/2021.repl4nlp-1.26</identifier>
<location>
<url>https://aclanthology.org/2021.repl4nlp-1.26</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>248</start>
<end>262</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Deriving Contextualised Semantic Features from BERT (and Other Transformer Model) Embeddings
%A Turton, Jacob
%A Smith, Robert Elliott
%A Vinson, David
%Y Rogers, Anna
%Y Calixto, Iacer
%Y Vulić, Ivan
%Y Saphra, Naomi
%Y Kassner, Nora
%Y Camburu, Oana-Maria
%Y Bansal, Trapit
%Y Shwartz, Vered
%S Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F turton-etal-2021-deriving
%X Models based on the transformer architecture, such as BERT, have marked a crucial step forward in the field of Natural Language Processing. Importantly, they allow the creation of word embeddings that capture important semantic information about words in context. However, as single entities, these embeddings are difficult to interpret and the models used to create them have been described as opaque. Binder and colleagues proposed an intuitive embedding space where each dimension is based on one of 65 core semantic features. Unfortunately, the space only exists for a small data-set of 535 words, limiting its uses. Previous work (Utsumi, 2018, 2020; Turton et al., 2020) has shown that Binder features can be derived from static embeddings and successfully extrapolated to a large new vocabulary. Taking the next step, this paper demonstrates that Binder features can be derived from the BERT embedding space. This provides two things; (1) semantic feature values derived from contextualised word embeddings and (2) insights into how semantic features are represented across the different layers of the BERT model.
%R 10.18653/v1/2021.repl4nlp-1.26
%U https://aclanthology.org/2021.repl4nlp-1.26
%U https://doi.org/10.18653/v1/2021.repl4nlp-1.26
%P 248-262
Markdown (Informal)
[Deriving Contextualised Semantic Features from BERT (and Other Transformer Model) Embeddings](https://aclanthology.org/2021.repl4nlp-1.26) (Turton et al., RepL4NLP 2021)
ACL