@inproceedings{loureiro-etal-2022-timelms,
title = "{T}ime{LM}s: Diachronic Language Models from {T}witter",
author = "Loureiro, Daniel and
Barbieri, Francesco and
Neves, Leonardo and
Espinosa Anke, Luis and
Camacho-collados, Jose",
editor = "Basile, Valerio and
Kozareva, Zornitsa and
Stajner, Sanja",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-demo.25",
doi = "10.18653/v1/2022.acl-demo.25",
pages = "251--260",
abstract = "Despite its importance, the time variable has been largely neglected in the NLP and language model literature. In this paper, we present TimeLMs, a set of language models specialized on diachronic Twitter data. We show that a continual learning strategy contributes to enhancing Twitter-based language models{'} capacity to deal with future and out-of-distribution tweets, while making them competitive with standardized and more monolithic benchmarks. We also perform a number of qualitative analyses showing how they cope with trends and peaks in activity involving specific named entities or concept drift. TimeLMs is available at github.com/cardiffnlp/timelms.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="loureiro-etal-2022-timelms">
<titleInfo>
<title>TimeLMs: Diachronic Language Models from Twitter</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Loureiro</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">Luis</namePart>
<namePart type="family">Espinosa Anke</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>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Valerio</namePart>
<namePart type="family">Basile</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanja</namePart>
<namePart type="family">Stajner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Despite its importance, the time variable has been largely neglected in the NLP and language model literature. In this paper, we present TimeLMs, a set of language models specialized on diachronic Twitter data. We show that a continual learning strategy contributes to enhancing Twitter-based language models’ capacity to deal with future and out-of-distribution tweets, while making them competitive with standardized and more monolithic benchmarks. We also perform a number of qualitative analyses showing how they cope with trends and peaks in activity involving specific named entities or concept drift. TimeLMs is available at github.com/cardiffnlp/timelms.</abstract>
<identifier type="citekey">loureiro-etal-2022-timelms</identifier>
<identifier type="doi">10.18653/v1/2022.acl-demo.25</identifier>
<location>
<url>https://aclanthology.org/2022.acl-demo.25</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>251</start>
<end>260</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TimeLMs: Diachronic Language Models from Twitter
%A Loureiro, Daniel
%A Barbieri, Francesco
%A Neves, Leonardo
%A Espinosa Anke, Luis
%A Camacho-collados, Jose
%Y Basile, Valerio
%Y Kozareva, Zornitsa
%Y Stajner, Sanja
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F loureiro-etal-2022-timelms
%X Despite its importance, the time variable has been largely neglected in the NLP and language model literature. In this paper, we present TimeLMs, a set of language models specialized on diachronic Twitter data. We show that a continual learning strategy contributes to enhancing Twitter-based language models’ capacity to deal with future and out-of-distribution tweets, while making them competitive with standardized and more monolithic benchmarks. We also perform a number of qualitative analyses showing how they cope with trends and peaks in activity involving specific named entities or concept drift. TimeLMs is available at github.com/cardiffnlp/timelms.
%R 10.18653/v1/2022.acl-demo.25
%U https://aclanthology.org/2022.acl-demo.25
%U https://doi.org/10.18653/v1/2022.acl-demo.25
%P 251-260
Markdown (Informal)
[TimeLMs: Diachronic Language Models from Twitter](https://aclanthology.org/2022.acl-demo.25) (Loureiro et al., ACL 2022)
ACL
- Daniel Loureiro, Francesco Barbieri, Leonardo Neves, Luis Espinosa Anke, and Jose Camacho-collados. 2022. TimeLMs: Diachronic Language Models from Twitter. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 251–260, Dublin, Ireland. Association for Computational Linguistics.