Decoupling Encoder and Decoder Networks for Abstractive Document Summarization

Ying Xu, Jey Han Lau, Timothy Baldwin, Trevor Cohn
<span title="">2017</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/mbsbsi6kgbe77pvpnznuhcvrde" style="color: black;">Proceedings of the MultiLing 2017 Workshop on Summarization and Summary Evaluation Across Source Types and Genres</a> </i> &nbsp;
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
more &raquo; ... 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.
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/w17-1002">doi:10.18653/v1/w17-1002</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/acl-multiling/XuLBC17.html">dblp:conf/acl-multiling/XuLBC17</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/w4ubwwqdpjdwxo4rqjwh4bi3si">fatcat:w4ubwwqdpjdwxo4rqjwh4bi3si</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200505035303/https://www.aclweb.org/anthology/W17-1002.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/52/be/52befcce203f318c457384d3ad159584b350a3d2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/w17-1002"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>