<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jiang-bansal-2018-closed">
    <titleInfo>
        <title>Closed-Book Training to Improve Summarization Encoder Memory</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yichen</namePart>
        <namePart type="family">Jiang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mohit</namePart>
        <namePart type="family">Bansal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-oct-nov</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ellen</namePart>
            <namePart type="family">Riloff</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Chiang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Julia</namePart>
            <namePart type="family">Hockenmaier</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jun’ichi</namePart>
            <namePart type="family">Tsujii</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Brussels, Belgium</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>A good neural sequence-to-sequence summarization model should have a strong encoder that can distill and memorize the important information from long input texts so that the decoder can generate salient summaries based on the encoder’s memory. In this paper, we aim to improve the memorization capabilities of the encoder of a pointer-generator model by adding an additional ‘closed-book’ decoder without attention and pointer mechanisms. Such a decoder forces the encoder to be more selective in the information encoded in its memory state because the decoder can’t rely on the extra information provided by the attention and possibly copy modules, and hence improves the entire model. On the CNN/Daily Mail dataset, our 2-decoder model outperforms the baseline significantly in terms of ROUGE and METEOR metrics, for both cross-entropy and reinforced setups (and on human evaluation). Moreover, our model also achieves higher scores in a test-only DUC-2002 generalizability setup. We further present a memory ability test, two saliency metrics, as well as several sanity-check ablations (based on fixed-encoder, gradient-flow cut, and model capacity) to prove that the encoder of our 2-decoder model does in fact learn stronger memory representations than the baseline encoder.</abstract>
    <identifier type="citekey">jiang-bansal-2018-closed</identifier>
    <identifier type="doi">10.18653/v1/D18-1440</identifier>
    <location>
        <url>https://aclanthology.org/D18-1440</url>
    </location>
    <part>
        <date>2018-oct-nov</date>
        <extent unit="page">
            <start>4067</start>
            <end>4077</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Closed-Book Training to Improve Summarization Encoder Memory
%A Jiang, Yichen
%A Bansal, Mohit
%Y Riloff, Ellen
%Y Chiang, David
%Y Hockenmaier, Julia
%Y Tsujii, Jun’ichi
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F jiang-bansal-2018-closed
%X A good neural sequence-to-sequence summarization model should have a strong encoder that can distill and memorize the important information from long input texts so that the decoder can generate salient summaries based on the encoder’s memory. In this paper, we aim to improve the memorization capabilities of the encoder of a pointer-generator model by adding an additional ‘closed-book’ decoder without attention and pointer mechanisms. Such a decoder forces the encoder to be more selective in the information encoded in its memory state because the decoder can’t rely on the extra information provided by the attention and possibly copy modules, and hence improves the entire model. On the CNN/Daily Mail dataset, our 2-decoder model outperforms the baseline significantly in terms of ROUGE and METEOR metrics, for both cross-entropy and reinforced setups (and on human evaluation). Moreover, our model also achieves higher scores in a test-only DUC-2002 generalizability setup. We further present a memory ability test, two saliency metrics, as well as several sanity-check ablations (based on fixed-encoder, gradient-flow cut, and model capacity) to prove that the encoder of our 2-decoder model does in fact learn stronger memory representations than the baseline encoder.
%R 10.18653/v1/D18-1440
%U https://aclanthology.org/D18-1440
%U https://doi.org/10.18653/v1/D18-1440
%P 4067-4077

Markdown (Informal)

[Closed-Book Training to Improve Summarization Encoder Memory](https://aclanthology.org/D18-1440) (Jiang & Bansal, EMNLP 2018)

• Closed-Book Training to Improve Summarization Encoder Memory (Jiang & Bansal, EMNLP 2018)

ACL

• Yichen Jiang and Mohit Bansal. 2018. Closed-Book Training to Improve Summarization Encoder Memory. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4067–4077, Brussels, Belgium. Association for Computational Linguistics.