@inproceedings{brock-etal-2022-textstar,
title = "Textstar: a Fast and Lightweight Graph-Based Algorithm for Extractive Summarization and Keyphrase Extraction",
author = "Brock, David and
Khan, Ali and
Doan, Tam and
Lin, Alicia and
Guo, Yifan and
Tarau, Paul",
editor = "Parameswaran, Pradeesh and
Biggs, Jennifer and
Powers, David",
booktitle = "Proceedings of the 20th Annual Workshop of the Australasian Language Technology Association",
month = dec,
year = "2022",
address = "Adelaide, Australia",
publisher = "Australasian Language Technology Association",
url = "https://aclanthology.org/2022.alta-1.22",
pages = "161--169",
abstract = "We introduce Textstar, a graph-based summarization and keyphrase extraction system that builds a document graph using only lemmatization and POS tagging. The document graph aggregates connections between lemma and sentence identifier nodes. Consecutive lemmas in each sentence, as well as consecutive sentences themselves, are connected in rings to form a ring of rings representing the document. We iteratively apply a centrality algorithm of our choice to the document graph and trim the lowest ranked nodes at each step. After the desired number of remaining sentences and lemmas is reached, we extract the sentences as the summary, and the remaining lemmas are aggregated into keyphrases using their context. Our algorithm is efficient enough to one-shot process large document graphs without any training, and empirical evaluation on several benchmarks indicates that our performance is higher than most other graph based algorithms.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="brock-etal-2022-textstar">
<titleInfo>
<title>Textstar: a Fast and Lightweight Graph-Based Algorithm for Extractive Summarization and Keyphrase Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Brock</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tam</namePart>
<namePart type="family">Doan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alicia</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifan</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Tarau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th Annual Workshop of the Australasian Language Technology Association</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pradeesh</namePart>
<namePart type="family">Parameswaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jennifer</namePart>
<namePart type="family">Biggs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Powers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Australasian Language Technology Association</publisher>
<place>
<placeTerm type="text">Adelaide, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce Textstar, a graph-based summarization and keyphrase extraction system that builds a document graph using only lemmatization and POS tagging. The document graph aggregates connections between lemma and sentence identifier nodes. Consecutive lemmas in each sentence, as well as consecutive sentences themselves, are connected in rings to form a ring of rings representing the document. We iteratively apply a centrality algorithm of our choice to the document graph and trim the lowest ranked nodes at each step. After the desired number of remaining sentences and lemmas is reached, we extract the sentences as the summary, and the remaining lemmas are aggregated into keyphrases using their context. Our algorithm is efficient enough to one-shot process large document graphs without any training, and empirical evaluation on several benchmarks indicates that our performance is higher than most other graph based algorithms.</abstract>
<identifier type="citekey">brock-etal-2022-textstar</identifier>
<location>
<url>https://aclanthology.org/2022.alta-1.22</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>161</start>
<end>169</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Textstar: a Fast and Lightweight Graph-Based Algorithm for Extractive Summarization and Keyphrase Extraction
%A Brock, David
%A Khan, Ali
%A Doan, Tam
%A Lin, Alicia
%A Guo, Yifan
%A Tarau, Paul
%Y Parameswaran, Pradeesh
%Y Biggs, Jennifer
%Y Powers, David
%S Proceedings of the 20th Annual Workshop of the Australasian Language Technology Association
%D 2022
%8 December
%I Australasian Language Technology Association
%C Adelaide, Australia
%F brock-etal-2022-textstar
%X We introduce Textstar, a graph-based summarization and keyphrase extraction system that builds a document graph using only lemmatization and POS tagging. The document graph aggregates connections between lemma and sentence identifier nodes. Consecutive lemmas in each sentence, as well as consecutive sentences themselves, are connected in rings to form a ring of rings representing the document. We iteratively apply a centrality algorithm of our choice to the document graph and trim the lowest ranked nodes at each step. After the desired number of remaining sentences and lemmas is reached, we extract the sentences as the summary, and the remaining lemmas are aggregated into keyphrases using their context. Our algorithm is efficient enough to one-shot process large document graphs without any training, and empirical evaluation on several benchmarks indicates that our performance is higher than most other graph based algorithms.
%U https://aclanthology.org/2022.alta-1.22
%P 161-169
Markdown (Informal)
[Textstar: a Fast and Lightweight Graph-Based Algorithm for Extractive Summarization and Keyphrase Extraction](https://aclanthology.org/2022.alta-1.22) (Brock et al., ALTA 2022)
ACL