@article{hayashi-etal-2021-wikiasp,
title = "{W}iki{A}sp: A Dataset for Multi-domain Aspect-based Summarization",
author = "Hayashi, Hiroaki and
Budania, Prashant and
Wang, Peng and
Ackerson, Chris and
Neervannan, Raj and
Neubig, Graham",
editor = "Roark, Brian and
Nenkova, Ani",
journal = "Transactions of the Association for Computational Linguistics",
volume = "9",
year = "2021",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2021.tacl-1.13/",
doi = "10.1162/tacl_a_00362",
pages = "211--225",
abstract = "Aspect-based summarization is the task of generating focused summaries based on specific points of interest. Such summaries aid efficient analysis of text, such as quickly understanding reviews or opinions from different angles. However, due to large differences in the type of aspects for different domains (e.g., sentiment, product features), the development of previous models has tended to be domain-specific. In this paper, we propose WikiAsp,1 a large-scale dataset for multi-domain aspect- based summarization that attempts to spur research in the direction of open-domain aspect-based summarization. Specifically, we build the dataset using Wikipedia articles from 20 different domains, using the section titles and boundaries of each article as a proxy for aspect annotation. We propose several straightforward baseline models for this task and conduct experiments on the dataset. Results highlight key challenges that existing summarization models face in this setting, such as proper pronoun handling of quoted sources and consistent explanation of time-sensitive events."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hayashi-etal-2021-wikiasp">
<titleInfo>
<title>WikiAsp: A Dataset for Multi-domain Aspect-based Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hiroaki</namePart>
<namePart type="family">Hayashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prashant</namePart>
<namePart type="family">Budania</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Ackerson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="family">Neervannan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Neubig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>Aspect-based summarization is the task of generating focused summaries based on specific points of interest. Such summaries aid efficient analysis of text, such as quickly understanding reviews or opinions from different angles. However, due to large differences in the type of aspects for different domains (e.g., sentiment, product features), the development of previous models has tended to be domain-specific. In this paper, we propose WikiAsp,1 a large-scale dataset for multi-domain aspect- based summarization that attempts to spur research in the direction of open-domain aspect-based summarization. Specifically, we build the dataset using Wikipedia articles from 20 different domains, using the section titles and boundaries of each article as a proxy for aspect annotation. We propose several straightforward baseline models for this task and conduct experiments on the dataset. Results highlight key challenges that existing summarization models face in this setting, such as proper pronoun handling of quoted sources and consistent explanation of time-sensitive events.</abstract>
<identifier type="citekey">hayashi-etal-2021-wikiasp</identifier>
<identifier type="doi">10.1162/tacl_a_00362</identifier>
<location>
<url>https://aclanthology.org/2021.tacl-1.13/</url>
</location>
<part>
<date>2021</date>
<detail type="volume"><number>9</number></detail>
<extent unit="page">
<start>211</start>
<end>225</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T WikiAsp: A Dataset for Multi-domain Aspect-based Summarization
%A Hayashi, Hiroaki
%A Budania, Prashant
%A Wang, Peng
%A Ackerson, Chris
%A Neervannan, Raj
%A Neubig, Graham
%J Transactions of the Association for Computational Linguistics
%D 2021
%V 9
%I MIT Press
%C Cambridge, MA
%F hayashi-etal-2021-wikiasp
%X Aspect-based summarization is the task of generating focused summaries based on specific points of interest. Such summaries aid efficient analysis of text, such as quickly understanding reviews or opinions from different angles. However, due to large differences in the type of aspects for different domains (e.g., sentiment, product features), the development of previous models has tended to be domain-specific. In this paper, we propose WikiAsp,1 a large-scale dataset for multi-domain aspect- based summarization that attempts to spur research in the direction of open-domain aspect-based summarization. Specifically, we build the dataset using Wikipedia articles from 20 different domains, using the section titles and boundaries of each article as a proxy for aspect annotation. We propose several straightforward baseline models for this task and conduct experiments on the dataset. Results highlight key challenges that existing summarization models face in this setting, such as proper pronoun handling of quoted sources and consistent explanation of time-sensitive events.
%R 10.1162/tacl_a_00362
%U https://aclanthology.org/2021.tacl-1.13/
%U https://doi.org/10.1162/tacl_a_00362
%P 211-225
Markdown (Informal)
[WikiAsp: A Dataset for Multi-domain Aspect-based Summarization](https://aclanthology.org/2021.tacl-1.13/) (Hayashi et al., TACL 2021)
ACL