@inproceedings{do-etal-2023-unsupervised,
title = "Unsupervised Open-domain Keyphrase Generation",
author = "Do, Lam and
Akash, Pritom Saha and
Chang, Kevin Chen-Chuan",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.592",
doi = "10.18653/v1/2023.acl-long.592",
pages = "10614--10627",
abstract = "In this work, we study the problem of unsupervised open-domain keyphrase generation, where the objective is a keyphrase generation model that can be built without using human-labeled data and can perform consistently across domains. To solve this problem, we propose a seq2seq model that consists of two modules, namely phraseness and informativeness module, both of which can be built in an unsupervised and open-domain fashion. The phraseness module generates phrases, while the informativeness module guides the generation towards those that represent the core concepts of the text. We thoroughly evaluate our proposed method using eight benchmark datasets from different domains. Results on in-domain datasets show that our approach achieves state-of-the-art results compared with existing unsupervised models, and overall narrows the gap between supervised and unsupervised methods down to about 16{\%}. Furthermore, we demonstrate that our model performs consistently across domains, as it surpasses the baselines on out-of-domain datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="do-etal-2023-unsupervised">
<titleInfo>
<title>Unsupervised Open-domain Keyphrase Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lam</namePart>
<namePart type="family">Do</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pritom</namePart>
<namePart type="given">Saha</namePart>
<namePart type="family">Akash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="given">Chen-Chuan</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work, we study the problem of unsupervised open-domain keyphrase generation, where the objective is a keyphrase generation model that can be built without using human-labeled data and can perform consistently across domains. To solve this problem, we propose a seq2seq model that consists of two modules, namely phraseness and informativeness module, both of which can be built in an unsupervised and open-domain fashion. The phraseness module generates phrases, while the informativeness module guides the generation towards those that represent the core concepts of the text. We thoroughly evaluate our proposed method using eight benchmark datasets from different domains. Results on in-domain datasets show that our approach achieves state-of-the-art results compared with existing unsupervised models, and overall narrows the gap between supervised and unsupervised methods down to about 16%. Furthermore, we demonstrate that our model performs consistently across domains, as it surpasses the baselines on out-of-domain datasets.</abstract>
<identifier type="citekey">do-etal-2023-unsupervised</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.592</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.592</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>10614</start>
<end>10627</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unsupervised Open-domain Keyphrase Generation
%A Do, Lam
%A Akash, Pritom Saha
%A Chang, Kevin Chen-Chuan
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F do-etal-2023-unsupervised
%X In this work, we study the problem of unsupervised open-domain keyphrase generation, where the objective is a keyphrase generation model that can be built without using human-labeled data and can perform consistently across domains. To solve this problem, we propose a seq2seq model that consists of two modules, namely phraseness and informativeness module, both of which can be built in an unsupervised and open-domain fashion. The phraseness module generates phrases, while the informativeness module guides the generation towards those that represent the core concepts of the text. We thoroughly evaluate our proposed method using eight benchmark datasets from different domains. Results on in-domain datasets show that our approach achieves state-of-the-art results compared with existing unsupervised models, and overall narrows the gap between supervised and unsupervised methods down to about 16%. Furthermore, we demonstrate that our model performs consistently across domains, as it surpasses the baselines on out-of-domain datasets.
%R 10.18653/v1/2023.acl-long.592
%U https://aclanthology.org/2023.acl-long.592
%U https://doi.org/10.18653/v1/2023.acl-long.592
%P 10614-10627
Markdown (Informal)
[Unsupervised Open-domain Keyphrase Generation](https://aclanthology.org/2023.acl-long.592) (Do et al., ACL 2023)
ACL
- Lam Do, Pritom Saha Akash, and Kevin Chen-Chuan Chang. 2023. Unsupervised Open-domain Keyphrase Generation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10614–10627, Toronto, Canada. Association for Computational Linguistics.