@inproceedings{pranav-etal-2024-comparing-static,
title = "Comparing Static and Contextual Distributional Semantic Models on Intrinsic Tasks: An Evaluation on {M}andarin {C}hinese Datasets",
author = "Pranav, A and
Cong, Yan and
Chersoni, Emmanuele and
Hsu, Yu-Yin and
Lenci, Alessandro",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.320",
pages = "3610--3627",
abstract = "The field of Distributional Semantics has recently undergone important changes, with the contextual representations produced by Transformers taking the place of static word embeddings models. Noticeably, previous studies comparing the two types of vectors have only focused on the English language and a limited number of models. In our study, we present a comparative evaluation of static and contextualized distributional models for Mandarin Chinese, focusing on a range of intrinsic tasks. Our results reveal that static models remain stronger for some of the classical tasks that consider word meaning independent of context, while contextualized models excel in identifying semantic relations between word pairs and in the categorization of words into abstract semantic classes.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pranav-etal-2024-comparing-static">
<titleInfo>
<title>Comparing Static and Contextual Distributional Semantic Models on Intrinsic Tasks: An Evaluation on Mandarin Chinese Datasets</title>
</titleInfo>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="family">Pranav</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Cong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmanuele</namePart>
<namePart type="family">Chersoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu-Yin</namePart>
<namePart type="family">Hsu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</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 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</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>The field of Distributional Semantics has recently undergone important changes, with the contextual representations produced by Transformers taking the place of static word embeddings models. Noticeably, previous studies comparing the two types of vectors have only focused on the English language and a limited number of models. In our study, we present a comparative evaluation of static and contextualized distributional models for Mandarin Chinese, focusing on a range of intrinsic tasks. Our results reveal that static models remain stronger for some of the classical tasks that consider word meaning independent of context, while contextualized models excel in identifying semantic relations between word pairs and in the categorization of words into abstract semantic classes.</abstract>
<identifier type="citekey">pranav-etal-2024-comparing-static</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.320</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>3610</start>
<end>3627</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparing Static and Contextual Distributional Semantic Models on Intrinsic Tasks: An Evaluation on Mandarin Chinese Datasets
%A Pranav, A.
%A Cong, Yan
%A Chersoni, Emmanuele
%A Hsu, Yu-Yin
%A Lenci, Alessandro
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F pranav-etal-2024-comparing-static
%X The field of Distributional Semantics has recently undergone important changes, with the contextual representations produced by Transformers taking the place of static word embeddings models. Noticeably, previous studies comparing the two types of vectors have only focused on the English language and a limited number of models. In our study, we present a comparative evaluation of static and contextualized distributional models for Mandarin Chinese, focusing on a range of intrinsic tasks. Our results reveal that static models remain stronger for some of the classical tasks that consider word meaning independent of context, while contextualized models excel in identifying semantic relations between word pairs and in the categorization of words into abstract semantic classes.
%U https://aclanthology.org/2024.lrec-main.320
%P 3610-3627
Markdown (Informal)
[Comparing Static and Contextual Distributional Semantic Models on Intrinsic Tasks: An Evaluation on Mandarin Chinese Datasets](https://aclanthology.org/2024.lrec-main.320) (Pranav et al., LREC-COLING 2024)
ACL