@inproceedings{zhang-etal-2024-unveiling,
title = "Unveiling Semantic Information in Sentence Embeddings",
author = "Zhang, Leixin and
Burian, David and
John, Vojt{\v{e}}ch and
Bojar, Ond{\v{r}}ej",
editor = "Bonial, Claire and
Bonn, Julia and
Hwang, Jena D.",
booktitle = "Proceedings of the Fifth International Workshop on Designing Meaning Representations @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.dmr-1.5",
pages = "39--47",
abstract = "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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-unveiling">
<titleInfo>
<title>Unveiling Semantic Information in Sentence Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Leixin</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Burian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vojtěch</namePart>
<namePart type="family">John</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Bojar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Workshop on Designing Meaning Representations @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Claire</namePart>
<namePart type="family">Bonial</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Bonn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jena</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Hwang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>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.</abstract>
<identifier type="citekey">zhang-etal-2024-unveiling</identifier>
<location>
<url>https://aclanthology.org/2024.dmr-1.5</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>39</start>
<end>47</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unveiling Semantic Information in Sentence Embeddings
%A Zhang, Leixin
%A Burian, David
%A John, Vojtěch
%A Bojar, Ondřej
%Y Bonial, Claire
%Y Bonn, Julia
%Y Hwang, Jena D.
%S Proceedings of the Fifth International Workshop on Designing Meaning Representations @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F zhang-etal-2024-unveiling
%X 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.
%U https://aclanthology.org/2024.dmr-1.5
%P 39-47
Markdown (Informal)
[Unveiling Semantic Information in Sentence Embeddings](https://aclanthology.org/2024.dmr-1.5) (Zhang et al., DMR-WS 2024)
ACL
- Leixin Zhang, David Burian, Vojtěch John, and Ondřej Bojar. 2024. Unveiling Semantic Information in Sentence Embeddings. In Proceedings of the Fifth International Workshop on Designing Meaning Representations @ LREC-COLING 2024, pages 39–47, Torino, Italia. ELRA and ICCL.