@inproceedings{theron-2023-contextualizing,
title = "Contextualizing the Limits of Model {\&} Evaluation Dataset Curation on Semantic Similarity Classification Tasks",
author = "Theron, Daniel",
editor = "Gehrmann, Sebastian and
Wang, Alex and
Sedoc, Jo{\~a}o and
Clark, Elizabeth and
Dhole, Kaustubh and
Chandu, Khyathi Raghavi and
Santus, Enrico and
Sedghamiz, Hooman",
booktitle = "Proceedings of the Third Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.gem-1.1",
pages = "1--8",
abstract = "This paper demonstrates how the limitations of pre-trained models and open evaluation datasets factor into assessing the performance of binary semantic similarity classification tasks. As (1) end-user-facing documentation around the curation of these datasets and pre-trained model training regimes is often not easily accessible and (2) given the lower friction and higher demand to quickly deploy such systems in real-world contexts, our study reinforces prior work showing performance disparities across datasets, embedding techniques and distance metrics, while highlighting the importance of understanding how data is collected, curated and analyzed in semantic similarity classification.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="theron-2023-contextualizing">
<titleInfo>
<title>Contextualizing the Limits of Model & Evaluation Dataset Curation on Semantic Similarity Classification Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Theron</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Gehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Clark</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaustubh</namePart>
<namePart type="family">Dhole</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khyathi</namePart>
<namePart type="given">Raghavi</namePart>
<namePart type="family">Chandu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hooman</namePart>
<namePart type="family">Sedghamiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper demonstrates how the limitations of pre-trained models and open evaluation datasets factor into assessing the performance of binary semantic similarity classification tasks. As (1) end-user-facing documentation around the curation of these datasets and pre-trained model training regimes is often not easily accessible and (2) given the lower friction and higher demand to quickly deploy such systems in real-world contexts, our study reinforces prior work showing performance disparities across datasets, embedding techniques and distance metrics, while highlighting the importance of understanding how data is collected, curated and analyzed in semantic similarity classification.</abstract>
<identifier type="citekey">theron-2023-contextualizing</identifier>
<location>
<url>https://aclanthology.org/2023.gem-1.1</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>1</start>
<end>8</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Contextualizing the Limits of Model & Evaluation Dataset Curation on Semantic Similarity Classification Tasks
%A Theron, Daniel
%Y Gehrmann, Sebastian
%Y Wang, Alex
%Y Sedoc, João
%Y Clark, Elizabeth
%Y Dhole, Kaustubh
%Y Chandu, Khyathi Raghavi
%Y Santus, Enrico
%Y Sedghamiz, Hooman
%S Proceedings of the Third Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F theron-2023-contextualizing
%X This paper demonstrates how the limitations of pre-trained models and open evaluation datasets factor into assessing the performance of binary semantic similarity classification tasks. As (1) end-user-facing documentation around the curation of these datasets and pre-trained model training regimes is often not easily accessible and (2) given the lower friction and higher demand to quickly deploy such systems in real-world contexts, our study reinforces prior work showing performance disparities across datasets, embedding techniques and distance metrics, while highlighting the importance of understanding how data is collected, curated and analyzed in semantic similarity classification.
%U https://aclanthology.org/2023.gem-1.1
%P 1-8
Markdown (Informal)
[Contextualizing the Limits of Model & Evaluation Dataset Curation on Semantic Similarity Classification Tasks](https://aclanthology.org/2023.gem-1.1) (Theron, GEM-WS 2023)
ACL