@inproceedings{xu-etal-2017-decoupling,
title = "Decoupling Encoder and Decoder Networks for Abstractive Document Summarization",
author = "Xu, Ying and
Lau, Jey Han and
Baldwin, Timothy and
Cohn, Trevor",
editor = "Giannakopoulos, George and
Lloret, Elena and
Conroy, John M. and
Steinberger, Josef and
Litvak, Marina and
Rankel, Peter and
Favre, Benoit",
booktitle = "Proceedings of the {M}ulti{L}ing 2017 Workshop on Summarization and Summary Evaluation Across Source Types and Genres",
month = apr,
year = "2017",
address = "Valencia, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-1002",
doi = "10.18653/v1/W17-1002",
pages = "7--11",
abstract = "Abstractive document summarization seeks to automatically generate a summary for a document, based on some abstract {``}understanding{''} of the original document. State-of-the-art techniques traditionally use attentive encoder{--}decoder architectures. However, due to the large number of parameters in these models, they require large training datasets and long training times. In this paper, we propose decoupling the encoder and decoder networks, and training them separately. We encode documents using an unsupervised document encoder, and then feed the document vector to a recurrent neural network decoder. With this decoupled architecture, we decrease the number of parameters in the decoder substantially, and shorten its training time. Experiments show that the decoupled model achieves comparable performance with state-of-the-art models for in-domain documents, but less well for out-of-domain documents.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2017-decoupling">
<titleInfo>
<title>Decoupling Encoder and Decoder Networks for Abstractive Document Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ying</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jey</namePart>
<namePart type="given">Han</namePart>
<namePart type="family">Lau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the MultiLing 2017 Workshop on Summarization and Summary Evaluation Across Source Types and Genres</title>
</titleInfo>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Giannakopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Lloret</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Conroy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="family">Steinberger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marina</namePart>
<namePart type="family">Litvak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Rankel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benoit</namePart>
<namePart type="family">Favre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Valencia, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Abstractive document summarization seeks to automatically generate a summary for a document, based on some abstract “understanding” of the original document. State-of-the-art techniques traditionally use attentive encoder–decoder architectures. However, due to the large number of parameters in these models, they require large training datasets and long training times. In this paper, we propose decoupling the encoder and decoder networks, and training them separately. We encode documents using an unsupervised document encoder, and then feed the document vector to a recurrent neural network decoder. With this decoupled architecture, we decrease the number of parameters in the decoder substantially, and shorten its training time. Experiments show that the decoupled model achieves comparable performance with state-of-the-art models for in-domain documents, but less well for out-of-domain documents.</abstract>
<identifier type="citekey">xu-etal-2017-decoupling</identifier>
<identifier type="doi">10.18653/v1/W17-1002</identifier>
<location>
<url>https://aclanthology.org/W17-1002</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>7</start>
<end>11</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Decoupling Encoder and Decoder Networks for Abstractive Document Summarization
%A Xu, Ying
%A Lau, Jey Han
%A Baldwin, Timothy
%A Cohn, Trevor
%Y Giannakopoulos, George
%Y Lloret, Elena
%Y Conroy, John M.
%Y Steinberger, Josef
%Y Litvak, Marina
%Y Rankel, Peter
%Y Favre, Benoit
%S Proceedings of the MultiLing 2017 Workshop on Summarization and Summary Evaluation Across Source Types and Genres
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F xu-etal-2017-decoupling
%X Abstractive document summarization seeks to automatically generate a summary for a document, based on some abstract “understanding” of the original document. State-of-the-art techniques traditionally use attentive encoder–decoder architectures. However, due to the large number of parameters in these models, they require large training datasets and long training times. In this paper, we propose decoupling the encoder and decoder networks, and training them separately. We encode documents using an unsupervised document encoder, and then feed the document vector to a recurrent neural network decoder. With this decoupled architecture, we decrease the number of parameters in the decoder substantially, and shorten its training time. Experiments show that the decoupled model achieves comparable performance with state-of-the-art models for in-domain documents, but less well for out-of-domain documents.
%R 10.18653/v1/W17-1002
%U https://aclanthology.org/W17-1002
%U https://doi.org/10.18653/v1/W17-1002
%P 7-11
Markdown (Informal)
[Decoupling Encoder and Decoder Networks for Abstractive Document Summarization](https://aclanthology.org/W17-1002) (Xu et al., MultiLing 2017)
ACL