<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="araujo-etal-2022-relevant">
    <titleInfo>
        <title>How Relevant is Selective Memory Population in Lifelong Language Learning?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Vladimir</namePart>
        <namePart type="family">Araujo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Helena</namePart>
        <namePart type="family">Balabin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Julio</namePart>
        <namePart type="family">Hurtado</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alvaro</namePart>
        <namePart type="family">Soto</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Marie-Francine</namePart>
        <namePart type="family">Moens</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online only</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Lifelong language learning seeks to have models continuously learn multiple tasks in a sequential order without suffering from catastrophic forgetting. State-of-the-art approaches rely on sparse experience replay as the primary approach to prevent forgetting. Experience replay usually adopts sampling methods for the memory population; however, the effect of the chosen sampling strategy on model performance has not yet been studied. In this paper, we investigate how relevant the selective memory population is in the lifelong learning process of text classification and question-answering tasks. We found that methods that randomly store a uniform number of samples from the entire data stream lead to high performances, especially for low memory size, which is consistent with computer vision studies.</abstract>
    <identifier type="citekey">araujo-etal-2022-relevant</identifier>
    <location>
        <url>https://aclanthology.org/2022.aacl-short.20</url>
    </location>
    <part>
        <date>2022-11</date>
        <extent unit="page">
            <start>154</start>
            <end>160</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T How Relevant is Selective Memory Population in Lifelong Language Learning?
%A Araujo, Vladimir
%A Balabin, Helena
%A Hurtado, Julio
%A Soto, Alvaro
%A Moens, Marie-Francine
%S Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online only
%F araujo-etal-2022-relevant
%X Lifelong language learning seeks to have models continuously learn multiple tasks in a sequential order without suffering from catastrophic forgetting. State-of-the-art approaches rely on sparse experience replay as the primary approach to prevent forgetting. Experience replay usually adopts sampling methods for the memory population; however, the effect of the chosen sampling strategy on model performance has not yet been studied. In this paper, we investigate how relevant the selective memory population is in the lifelong learning process of text classification and question-answering tasks. We found that methods that randomly store a uniform number of samples from the entire data stream lead to high performances, especially for low memory size, which is consistent with computer vision studies.
%U https://aclanthology.org/2022.aacl-short.20
%P 154-160

Markdown (Informal)

[How Relevant is Selective Memory Population in Lifelong Language Learning?](https://aclanthology.org/2022.aacl-short.20) (Araujo et al., AACL-IJCNLP 2022)

• How Relevant is Selective Memory Population in Lifelong Language Learning? (Araujo et al., AACL-IJCNLP 2022)

ACL

• Vladimir Araujo, Helena Balabin, Julio Hurtado, Alvaro Soto, and Marie-Francine Moens. 2022. How Relevant is Selective Memory Population in Lifelong Language Learning?. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 154–160, Online only. Association for Computational Linguistics.