<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-cheng-2022-r">
    <titleInfo>
        <title>R-TeaFor: Regularized Teacher-Forcing for Abstractive Summarization</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Guan-Yu</namePart>
        <namePart type="family">Lin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pu-Jen</namePart>
        <namePart type="family">Cheng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yoav</namePart>
            <namePart type="family">Goldberg</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">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Teacher-forcing is widely used in training sequence generation models to improve sampling efficiency and to stabilize training. However, teacher-forcing is vulnerable to the exposure bias problem. Previous works have attempted to address exposure bias by modifying the training data to simulate model-generated results. Nevertheless, they do not consider the pairwise relationship between the original training data and the modified ones, which provides more information during training. Hence, we propose Regularized Teacher-Forcing (R-TeaFor) to utilize this relationship for better regularization. Empirically, our experiments show that R-TeaFor outperforms previous summarization state-of-the-art models, and the results can be generalized to different pre-trained models.</abstract>
    <identifier type="citekey">lin-cheng-2022-r</identifier>
    <identifier type="doi">10.18653/v1/2022.emnlp-main.423</identifier>
    <location>
        <url>https://aclanthology.org/2022.emnlp-main.423</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>6303</start>
            <end>6311</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T R-TeaFor: Regularized Teacher-Forcing for Abstractive Summarization
%A Lin, Guan-Yu
%A Cheng, Pu-Jen
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F lin-cheng-2022-r
%X Teacher-forcing is widely used in training sequence generation models to improve sampling efficiency and to stabilize training. However, teacher-forcing is vulnerable to the exposure bias problem. Previous works have attempted to address exposure bias by modifying the training data to simulate model-generated results. Nevertheless, they do not consider the pairwise relationship between the original training data and the modified ones, which provides more information during training. Hence, we propose Regularized Teacher-Forcing (R-TeaFor) to utilize this relationship for better regularization. Empirically, our experiments show that R-TeaFor outperforms previous summarization state-of-the-art models, and the results can be generalized to different pre-trained models.
%R 10.18653/v1/2022.emnlp-main.423
%U https://aclanthology.org/2022.emnlp-main.423
%U https://doi.org/10.18653/v1/2022.emnlp-main.423
%P 6303-6311

Markdown (Informal)

[R-TeaFor: Regularized Teacher-Forcing for Abstractive Summarization](https://aclanthology.org/2022.emnlp-main.423) (Lin & Cheng, EMNLP 2022)

• R-TeaFor: Regularized Teacher-Forcing for Abstractive Summarization (Lin & Cheng, EMNLP 2022)

ACL

• Guan-Yu Lin and Pu-Jen Cheng. 2022. R-TeaFor: Regularized Teacher-Forcing for Abstractive Summarization. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 6303–6311, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.