@inproceedings{antypas-etal-2023-supertweeteval,
title = "{S}uper{T}weet{E}val: A Challenging, Unified and Heterogeneous Benchmark for Social Media {NLP} Research",
author = "Antypas, Dimosthenis and
Ushio, Asahi and
Barbieri, Francesco and
Neves, Leonardo and
Rezaee, Kiamehr and
Espinosa-Anke, Luis and
Pei, Jiaxin and
Camacho-Collados, Jose",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.838",
doi = "10.18653/v1/2023.findings-emnlp.838",
pages = "12590--12607",
abstract = "Despite its relevance, the maturity of NLP for social media pales in comparison with general-purpose models, metrics and benchmarks. This fragmented landscape makes it hard for the community to know, for instance, given a task, which is the best performing model and how it compares with others. To alleviate this issue, we introduce a unified benchmark for NLP evaluation in social media, SuperTweetEval, which includes a heterogeneous set of tasks and datasets combined, adapted and constructed from scratch. We benchmarked the performance of a wide range of models on SuperTweetEval and our results suggest that, despite the recent advances in language modelling, social media remains challenging.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="antypas-etal-2023-supertweeteval">
<titleInfo>
<title>SuperTweetEval: A Challenging, Unified and Heterogeneous Benchmark for Social Media NLP Research</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dimosthenis</namePart>
<namePart type="family">Antypas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asahi</namePart>
<namePart type="family">Ushio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francesco</namePart>
<namePart type="family">Barbieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leonardo</namePart>
<namePart type="family">Neves</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kiamehr</namePart>
<namePart type="family">Rezaee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Espinosa-Anke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaxin</namePart>
<namePart type="family">Pei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="family">Camacho-Collados</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>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</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>Despite its relevance, the maturity of NLP for social media pales in comparison with general-purpose models, metrics and benchmarks. This fragmented landscape makes it hard for the community to know, for instance, given a task, which is the best performing model and how it compares with others. To alleviate this issue, we introduce a unified benchmark for NLP evaluation in social media, SuperTweetEval, which includes a heterogeneous set of tasks and datasets combined, adapted and constructed from scratch. We benchmarked the performance of a wide range of models on SuperTweetEval and our results suggest that, despite the recent advances in language modelling, social media remains challenging.</abstract>
<identifier type="citekey">antypas-etal-2023-supertweeteval</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.838</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.838</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>12590</start>
<end>12607</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SuperTweetEval: A Challenging, Unified and Heterogeneous Benchmark for Social Media NLP Research
%A Antypas, Dimosthenis
%A Ushio, Asahi
%A Barbieri, Francesco
%A Neves, Leonardo
%A Rezaee, Kiamehr
%A Espinosa-Anke, Luis
%A Pei, Jiaxin
%A Camacho-Collados, Jose
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F antypas-etal-2023-supertweeteval
%X Despite its relevance, the maturity of NLP for social media pales in comparison with general-purpose models, metrics and benchmarks. This fragmented landscape makes it hard for the community to know, for instance, given a task, which is the best performing model and how it compares with others. To alleviate this issue, we introduce a unified benchmark for NLP evaluation in social media, SuperTweetEval, which includes a heterogeneous set of tasks and datasets combined, adapted and constructed from scratch. We benchmarked the performance of a wide range of models on SuperTweetEval and our results suggest that, despite the recent advances in language modelling, social media remains challenging.
%R 10.18653/v1/2023.findings-emnlp.838
%U https://aclanthology.org/2023.findings-emnlp.838
%U https://doi.org/10.18653/v1/2023.findings-emnlp.838
%P 12590-12607
Markdown (Informal)
[SuperTweetEval: A Challenging, Unified and Heterogeneous Benchmark for Social Media NLP Research](https://aclanthology.org/2023.findings-emnlp.838) (Antypas et al., Findings 2023)
ACL
- Dimosthenis Antypas, Asahi Ushio, Francesco Barbieri, Leonardo Neves, Kiamehr Rezaee, Luis Espinosa-Anke, Jiaxin Pei, and Jose Camacho-Collados. 2023. SuperTweetEval: A Challenging, Unified and Heterogeneous Benchmark for Social Media NLP Research. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 12590–12607, Singapore. Association for Computational Linguistics.