<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qin-etal-2020-using">
    <titleInfo>
        <title>Using the Past Knowledge to Improve Sentiment Classification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Qi</namePart>
        <namePart type="family">Qin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wenpeng</namePart>
        <namePart type="family">Hu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bing</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Trevor</namePart>
            <namePart type="family">Cohn</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yulan</namePart>
            <namePart type="family">He</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yang</namePart>
            <namePart type="family">Liu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper studies sentiment classification in the lifelong learning setting that incrementally learns a sequence of sentiment classification tasks. It proposes a new lifelong learning model (called L2PG) that can retain and selectively transfer the knowledge learned in the past to help learn the new task. A key innovation of this proposed model is a novel parameter-gate (p-gate) mechanism that regulates the flow or transfer of the previously learned knowledge to the new task. Specifically, it can selectively use the network parameters (which represent the retained knowledge gained from the previous tasks) to assist the learning of the new task t. Knowledge distillation is also employed in the process to preserve the past knowledge by approximating the network output at the state when task t-1 was learned. Experimental results show that L2PG outperforms strong baselines, including even multiple task learning.</abstract>
    <identifier type="citekey">qin-etal-2020-using</identifier>
    <identifier type="doi">10.18653/v1/2020.findings-emnlp.101</identifier>
    <location>
        <url>https://aclanthology.org/2020.findings-emnlp.101/</url>
    </location>
    <part>
        <date>2020-11</date>
        <extent unit="page">
            <start>1124</start>
            <end>1133</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Using the Past Knowledge to Improve Sentiment Classification
%A Qin, Qi
%A Hu, Wenpeng
%A Liu, Bing
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F qin-etal-2020-using
%X This paper studies sentiment classification in the lifelong learning setting that incrementally learns a sequence of sentiment classification tasks. It proposes a new lifelong learning model (called L2PG) that can retain and selectively transfer the knowledge learned in the past to help learn the new task. A key innovation of this proposed model is a novel parameter-gate (p-gate) mechanism that regulates the flow or transfer of the previously learned knowledge to the new task. Specifically, it can selectively use the network parameters (which represent the retained knowledge gained from the previous tasks) to assist the learning of the new task t. Knowledge distillation is also employed in the process to preserve the past knowledge by approximating the network output at the state when task t-1 was learned. Experimental results show that L2PG outperforms strong baselines, including even multiple task learning.
%R 10.18653/v1/2020.findings-emnlp.101
%U https://aclanthology.org/2020.findings-emnlp.101/
%U https://doi.org/10.18653/v1/2020.findings-emnlp.101
%P 1124-1133

Markdown (Informal)

[Using the Past Knowledge to Improve Sentiment Classification](https://aclanthology.org/2020.findings-emnlp.101/) (Qin et al., Findings 2020)

• Using the Past Knowledge to Improve Sentiment Classification (Qin et al., Findings 2020)

ACL

• Qi Qin, Wenpeng Hu, and Bing Liu. 2020. Using the Past Knowledge to Improve Sentiment Classification. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 1124–1133, Online. Association for Computational Linguistics.