LMFingerprints : Visual Explanations of Language Model Embedding Spaces through Layerwise Contextualization Scores
LMFingerprints : Visual Explanations of Language Model Embedding Spaces through Layerwise Contextualization Scores
No Thumbnail Available
Files
There are no files associated with this item.
Date
2022
Editors
Journal ISSN
Electronic ISSN
ISBN
Bibliographical data
Publisher
Series
DOI (citable link)
International patent number
Link to the license
EU project number
Project
Open Access publication
Title in another language
Publication type
Journal article
Publication status
Published
Published in
Computer Graphics Forum ; 41 (2022), 3. - pp. 295-307. - Wiley. - ISSN 0167-7055. - eISSN 1467-8659
Abstract
Language models, such as BERT, construct multiple, contextualized embeddings for each word occurrence in a corpus. Understanding how the contextualization propagates through the model's layers is crucial for deciding which layers to use for a specific analysis task. Currently, most embedding spaces are explained by probing classifiers; however, some findings remain inconclusive. In this paper, we present LMFingerprints, a novel scoring-based technique for the explanation of contextualized word embeddings. We introduce two categories of scoring functions, which measure (1) the degree of contextualization, i.e., the layerwise changes in the embedding vectors, and (2) the type of contextualization, i.e., the captured context information. We integrate these scores into an interactive explanation workspace. By combining visual and verbal elements, we provide an overview of contextualization in six popular transformer-based language models. We evaluate hypotheses from the domain of computational linguistics, and our results not only confirm findings from related work but also reveal new aspects about the information captured in the embedding spaces. For instance, we show that while numbers are poorly contextualized, stopwords have an unexpected high contextualization in the models' upper layers, where their neighborhoods shift from similar functionality tokens to tokens that contribute to the meaning of the surrounding sentences.
Summary in another language
Subject (DDC)
400 Philology, Linguistics
Keywords
Conference
Review
undefined / . - undefined, undefined. - (undefined; undefined)
Cite This
ISO 690
SEVASTJANOVA, Rita, Aikaterini-Lida KALOULI, Christin SCHÄTZLE, Hanna SCHÄFER, Mennatallah EL-ASSADY, 2022. LMFingerprints : Visual Explanations of Language Model Embedding Spaces through Layerwise Contextualization Scores. In: Computer Graphics Forum. Wiley. 41(3), pp. 295-307. ISSN 0167-7055. eISSN 1467-8659. Available under: doi: 10.1111/cgf.14541BibTex
@article{Sevastjanova2022-07-29LMFin-58281, year={2022}, doi={10.1111/cgf.14541}, title={LMFingerprints : Visual Explanations of Language Model Embedding Spaces through Layerwise Contextualization Scores}, number={3}, volume={41}, issn={0167-7055}, journal={Computer Graphics Forum}, pages={295--307}, author={Sevastjanova, Rita and Kalouli, Aikaterini-Lida and Schätzle, Christin and Schäfer, Hanna and El-Assady, Mennatallah} }
RDF
<rdf:RDF xmlns:dcterms="http://purl.org/dc/terms/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:bibo="http://purl.org/ontology/bibo/" xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:void="http://rdfs.org/ns/void#" xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/58281"> <dc:creator>Kalouli, Aikaterini-Lida</dc:creator> <dcterms:rights rdf:resource="http://creativecommons.org/licenses/by-nc-nd/4.0/"/> <dcterms:issued>2022-07-29</dcterms:issued> <dc:contributor>El-Assady, Mennatallah</dc:contributor> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-08-12T09:23:52Z</dcterms:available> <dc:contributor>Schätzle, Christin</dc:contributor> <dc:creator>Schäfer, Hanna</dc:creator> <dc:contributor>Kalouli, Aikaterini-Lida</dc:contributor> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dcterms:title>LMFingerprints : Visual Explanations of Language Model Embedding Spaces through Layerwise Contextualization Scores</dcterms:title> <foaf:homepage rdf:resource="http://localhost:8080/"/> <dc:contributor>Schäfer, Hanna</dc:contributor> <dc:language>eng</dc:language> <dc:creator>Sevastjanova, Rita</dc:creator> <dcterms:abstract xml:lang="eng">Language models, such as BERT, construct multiple, contextualized embeddings for each word occurrence in a corpus. Understanding how the contextualization propagates through the model's layers is crucial for deciding which layers to use for a specific analysis task. Currently, most embedding spaces are explained by probing classifiers; however, some findings remain inconclusive. In this paper, we present LMFingerprints, a novel scoring-based technique for the explanation of contextualized word embeddings. We introduce two categories of scoring functions, which measure (1) the degree of contextualization, i.e., the layerwise changes in the embedding vectors, and (2) the type of contextualization, i.e., the captured context information. We integrate these scores into an interactive explanation workspace. By combining visual and verbal elements, we provide an overview of contextualization in six popular transformer-based language models. We evaluate hypotheses from the domain of computational linguistics, and our results not only confirm findings from related work but also reveal new aspects about the information captured in the embedding spaces. For instance, we show that while numbers are poorly contextualized, stopwords have an unexpected high contextualization in the models' upper layers, where their neighborhoods shift from similar functionality tokens to tokens that contribute to the meaning of the surrounding sentences.</dcterms:abstract> <dc:creator>El-Assady, Mennatallah</dc:creator> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/> <dc:contributor>Sevastjanova, Rita</dc:contributor> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/58281"/> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/45"/> <dc:creator>Schätzle, Christin</dc:creator> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-08-12T09:23:52Z</dc:date> <dc:rights>Attribution-NonCommercial-NoDerivatives 4.0 International</dc:rights> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/45"/> </rdf:Description> </rdf:RDF>
Internal note
xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter
Examination date of dissertation
Method of financing
Comment on publication
Alliance license
Corresponding Authors der Uni Konstanz vorhanden
International Co-Authors
Bibliography of Konstanz
Yes
Refereed
Yes