@inproceedings{sharma-etal-2019-bigpatent,
title = "{BIGPATENT}: A Large-Scale Dataset for Abstractive and Coherent Summarization",
author = "Sharma, Eva and
Li, Chen and
Wang, Lu",
editor = "Korhonen, Anna and
Traum, David and
M{\`a}rquez, Llu{\'\i}s",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-1212",
doi = "10.18653/v1/P19-1212",
pages = "2204--2213",
abstract = "Most existing text summarization datasets are compiled from the news domain, where summaries have a flattened discourse structure. In such datasets, summary-worthy content often appears in the beginning of input articles. Moreover, large segments from input articles are present verbatim in their respective summaries. These issues impede the learning and evaluation of systems that can understand an article{'}s global content structure as well as produce abstractive summaries with high compression ratio. In this work, we present a novel dataset, BIGPATENT, consisting of 1.3 million records of U.S. patent documents along with human written abstractive summaries. Compared to existing summarization datasets, BIGPATENT has the following properties: i) summaries contain a richer discourse structure with more recurring entities, ii) salient content is evenly distributed in the input, and iii) lesser and shorter extractive fragments are present in the summaries. Finally, we train and evaluate baselines and popular learning models on BIGPATENT to shed light on new challenges and motivate future directions for summarization research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sharma-etal-2019-bigpatent">
<titleInfo>
<title>BIGPATENT: A Large-Scale Dataset for Abstractive and Coherent Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eva</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Traum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Màrquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Most existing text summarization datasets are compiled from the news domain, where summaries have a flattened discourse structure. In such datasets, summary-worthy content often appears in the beginning of input articles. Moreover, large segments from input articles are present verbatim in their respective summaries. These issues impede the learning and evaluation of systems that can understand an article’s global content structure as well as produce abstractive summaries with high compression ratio. In this work, we present a novel dataset, BIGPATENT, consisting of 1.3 million records of U.S. patent documents along with human written abstractive summaries. Compared to existing summarization datasets, BIGPATENT has the following properties: i) summaries contain a richer discourse structure with more recurring entities, ii) salient content is evenly distributed in the input, and iii) lesser and shorter extractive fragments are present in the summaries. Finally, we train and evaluate baselines and popular learning models on BIGPATENT to shed light on new challenges and motivate future directions for summarization research.</abstract>
<identifier type="citekey">sharma-etal-2019-bigpatent</identifier>
<identifier type="doi">10.18653/v1/P19-1212</identifier>
<location>
<url>https://aclanthology.org/P19-1212</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>2204</start>
<end>2213</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BIGPATENT: A Large-Scale Dataset for Abstractive and Coherent Summarization
%A Sharma, Eva
%A Li, Chen
%A Wang, Lu
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F sharma-etal-2019-bigpatent
%X Most existing text summarization datasets are compiled from the news domain, where summaries have a flattened discourse structure. In such datasets, summary-worthy content often appears in the beginning of input articles. Moreover, large segments from input articles are present verbatim in their respective summaries. These issues impede the learning and evaluation of systems that can understand an article’s global content structure as well as produce abstractive summaries with high compression ratio. In this work, we present a novel dataset, BIGPATENT, consisting of 1.3 million records of U.S. patent documents along with human written abstractive summaries. Compared to existing summarization datasets, BIGPATENT has the following properties: i) summaries contain a richer discourse structure with more recurring entities, ii) salient content is evenly distributed in the input, and iii) lesser and shorter extractive fragments are present in the summaries. Finally, we train and evaluate baselines and popular learning models on BIGPATENT to shed light on new challenges and motivate future directions for summarization research.
%R 10.18653/v1/P19-1212
%U https://aclanthology.org/P19-1212
%U https://doi.org/10.18653/v1/P19-1212
%P 2204-2213
Markdown (Informal)
[BIGPATENT: A Large-Scale Dataset for Abstractive and Coherent Summarization](https://aclanthology.org/P19-1212) (Sharma et al., ACL 2019)
ACL