Unveiling Semantic Information in Sentence Embeddings
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F24%3A10492919" target="_blank" >RIV/00216208:11320/24:10492919 - isvavai.cz</a>
Result on the web
<a href="https://aclanthology.org/2024.dmr-1.5/" target="_blank" >https://aclanthology.org/2024.dmr-1.5/</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Unveiling Semantic Information in Sentence Embeddings
Original language description
This study evaluates the extent to which semantic information is preserved within sentence embeddings generated from state-of-art sentence embedding models: SBERT and LaBSE. Specifically, we analyzed 13 semantic attributes in sentence embeddings. Our findings indicate that some semantic features (such as tense-related classes) can be decoded from the representation of sentence embeddings. Additionally, we discover the limitation of the current sentence embedding models: inferring meaning beyond the lexical level has proven to be difficult.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/GX19-26934X" target="_blank" >GX19-26934X: Neural Representations in Multi-modal and Multi-lingual Modeling</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the Fifth International Workshop on Designing Meaning Representations (DMR 2024) @ LREC-COLING 2024
ISBN
978-2-493-81439-5
ISSN
—
e-ISSN
—
Number of pages
9
Pages from-to
39-47
Publisher name
ELRA Language Resource Association
Place of publication
Paris, France
Event location
Torino, Italy
Event date
May 21, 2024
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—