@inproceedings{tsukagoshi-etal-2022-comparison,
title = "Comparison and Combination of Sentence Embeddings Derived from Different Supervision Signals",
author = "Tsukagoshi, Hayato and
Sasano, Ryohei and
Takeda, Koichi",
editor = "Nastase, Vivi and
Pavlick, Ellie and
Pilehvar, Mohammad Taher and
Camacho-Collados, Jose and
Raganato, Alessandro",
booktitle = "Proceedings of the 11th Joint Conference on Lexical and Computational Semantics",
month = jul,
year = "2022",
address = "Seattle, Washington",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.starsem-1.12",
doi = "10.18653/v1/2022.starsem-1.12",
pages = "139--150",
abstract = "There have been many successful applications of sentence embedding methods. However, it has not been well understood what properties are captured in the resulting sentence embeddings depending on the supervision signals. In this paper, we focus on two types of sentence embedding methods with similar architectures and tasks: one fine-tunes pre-trained language models on the natural language inference task, and the other fine-tunes pre-trained language models on word prediction task from its definition sentence, and investigate their properties. Specifically, we compare their performances on semantic textual similarity (STS) tasks using STS datasets partitioned from two perspectives: 1) sentence source and 2) superficial similarity of the sentence pairs, and compare their performances on the downstream and probing tasks. Furthermore, we attempt to combine the two methods and demonstrate that combining the two methods yields substantially better performance than the respective methods on unsupervised STS tasks and downstream tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tsukagoshi-etal-2022-comparison">
<titleInfo>
<title>Comparison and Combination of Sentence Embeddings Derived from Different Supervision Signals</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hayato</namePart>
<namePart type="family">Tsukagoshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryohei</namePart>
<namePart type="family">Sasano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koichi</namePart>
<namePart type="family">Takeda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 11th Joint Conference on Lexical and Computational Semantics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vivi</namePart>
<namePart type="family">Nastase</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ellie</namePart>
<namePart type="family">Pavlick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="family">Camacho-Collados</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Raganato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, Washington</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>There have been many successful applications of sentence embedding methods. However, it has not been well understood what properties are captured in the resulting sentence embeddings depending on the supervision signals. In this paper, we focus on two types of sentence embedding methods with similar architectures and tasks: one fine-tunes pre-trained language models on the natural language inference task, and the other fine-tunes pre-trained language models on word prediction task from its definition sentence, and investigate their properties. Specifically, we compare their performances on semantic textual similarity (STS) tasks using STS datasets partitioned from two perspectives: 1) sentence source and 2) superficial similarity of the sentence pairs, and compare their performances on the downstream and probing tasks. Furthermore, we attempt to combine the two methods and demonstrate that combining the two methods yields substantially better performance than the respective methods on unsupervised STS tasks and downstream tasks.</abstract>
<identifier type="citekey">tsukagoshi-etal-2022-comparison</identifier>
<identifier type="doi">10.18653/v1/2022.starsem-1.12</identifier>
<location>
<url>https://aclanthology.org/2022.starsem-1.12</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>139</start>
<end>150</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparison and Combination of Sentence Embeddings Derived from Different Supervision Signals
%A Tsukagoshi, Hayato
%A Sasano, Ryohei
%A Takeda, Koichi
%Y Nastase, Vivi
%Y Pavlick, Ellie
%Y Pilehvar, Mohammad Taher
%Y Camacho-Collados, Jose
%Y Raganato, Alessandro
%S Proceedings of the 11th Joint Conference on Lexical and Computational Semantics
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, Washington
%F tsukagoshi-etal-2022-comparison
%X There have been many successful applications of sentence embedding methods. However, it has not been well understood what properties are captured in the resulting sentence embeddings depending on the supervision signals. In this paper, we focus on two types of sentence embedding methods with similar architectures and tasks: one fine-tunes pre-trained language models on the natural language inference task, and the other fine-tunes pre-trained language models on word prediction task from its definition sentence, and investigate their properties. Specifically, we compare their performances on semantic textual similarity (STS) tasks using STS datasets partitioned from two perspectives: 1) sentence source and 2) superficial similarity of the sentence pairs, and compare their performances on the downstream and probing tasks. Furthermore, we attempt to combine the two methods and demonstrate that combining the two methods yields substantially better performance than the respective methods on unsupervised STS tasks and downstream tasks.
%R 10.18653/v1/2022.starsem-1.12
%U https://aclanthology.org/2022.starsem-1.12
%U https://doi.org/10.18653/v1/2022.starsem-1.12
%P 139-150
Markdown (Informal)
[Comparison and Combination of Sentence Embeddings Derived from Different Supervision Signals](https://aclanthology.org/2022.starsem-1.12) (Tsukagoshi et al., *SEM 2022)
ACL