@inproceedings{kim-etal-2020-learning,
title = "Learning {CNF} Blocking for Large-scale Author Name Disambiguation",
author = "Kim, Kunho and
Sefid, Athar and
Giles, C. Lee",
editor = "Chandrasekaran, Muthu Kumar and
de Waard, Anita and
Feigenblat, Guy and
Freitag, Dayne and
Ghosal, Tirthankar and
Hovy, Eduard and
Knoth, Petr and
Konopnicki, David and
Mayr, Philipp and
Patton, Robert M. and
Shmueli-Scheuer, Michal",
booktitle = "Proceedings of the First Workshop on Scholarly Document Processing",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.sdp-1.8/",
doi = "10.18653/v1/2020.sdp-1.8",
pages = "72--80",
abstract = "Author name disambiguation (AND) algorithms identify a unique author entity record from all similar or same publication records in scholarly or similar databases. Typically, a clustering method is used that requires calculation of similarities between each possible record pair. However, the total number of pairs grows quadratically with the size of the author database making such clustering difficult for millions of records. One remedy is a blocking function that reduces the number of pairwise similarity calculations. Here, we introduce a new way of learning blocking schemes by using a conjunctive normal form (CNF) in contrast to the disjunctive normal form (DNF). We demonstrate on PubMed author records that CNF blocking reduces more pairs while preserving high pairs completeness compared to the previous methods that use a DNF and that the computation time is significantly reduced. In addition, we also show how to ensure that the method produces disjoint blocks so that much of the AND algorithm can be efficiently paralleled. Our CNF blocking method is tested on the entire PubMed database of 80 million author mentions and efficiently removes 82.17{\%} of all author record pairs in 10 minutes."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2020-learning">
<titleInfo>
<title>Learning CNF Blocking for Large-scale Author Name Disambiguation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kunho</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Athar</namePart>
<namePart type="family">Sefid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">C</namePart>
<namePart type="given">Lee</namePart>
<namePart type="family">Giles</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Scholarly Document Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muthu</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Chandrasekaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anita</namePart>
<namePart type="family">de Waard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Feigenblat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dayne</namePart>
<namePart type="family">Freitag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tirthankar</namePart>
<namePart type="family">Ghosal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eduard</namePart>
<namePart type="family">Hovy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Petr</namePart>
<namePart type="family">Knoth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Konopnicki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Mayr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Patton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michal</namePart>
<namePart type="family">Shmueli-Scheuer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Author name disambiguation (AND) algorithms identify a unique author entity record from all similar or same publication records in scholarly or similar databases. Typically, a clustering method is used that requires calculation of similarities between each possible record pair. However, the total number of pairs grows quadratically with the size of the author database making such clustering difficult for millions of records. One remedy is a blocking function that reduces the number of pairwise similarity calculations. Here, we introduce a new way of learning blocking schemes by using a conjunctive normal form (CNF) in contrast to the disjunctive normal form (DNF). We demonstrate on PubMed author records that CNF blocking reduces more pairs while preserving high pairs completeness compared to the previous methods that use a DNF and that the computation time is significantly reduced. In addition, we also show how to ensure that the method produces disjoint blocks so that much of the AND algorithm can be efficiently paralleled. Our CNF blocking method is tested on the entire PubMed database of 80 million author mentions and efficiently removes 82.17% of all author record pairs in 10 minutes.</abstract>
<identifier type="citekey">kim-etal-2020-learning</identifier>
<identifier type="doi">10.18653/v1/2020.sdp-1.8</identifier>
<location>
<url>https://aclanthology.org/2020.sdp-1.8/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>72</start>
<end>80</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning CNF Blocking for Large-scale Author Name Disambiguation
%A Kim, Kunho
%A Sefid, Athar
%A Giles, C. Lee
%Y Chandrasekaran, Muthu Kumar
%Y de Waard, Anita
%Y Feigenblat, Guy
%Y Freitag, Dayne
%Y Ghosal, Tirthankar
%Y Hovy, Eduard
%Y Knoth, Petr
%Y Konopnicki, David
%Y Mayr, Philipp
%Y Patton, Robert M.
%Y Shmueli-Scheuer, Michal
%S Proceedings of the First Workshop on Scholarly Document Processing
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F kim-etal-2020-learning
%X Author name disambiguation (AND) algorithms identify a unique author entity record from all similar or same publication records in scholarly or similar databases. Typically, a clustering method is used that requires calculation of similarities between each possible record pair. However, the total number of pairs grows quadratically with the size of the author database making such clustering difficult for millions of records. One remedy is a blocking function that reduces the number of pairwise similarity calculations. Here, we introduce a new way of learning blocking schemes by using a conjunctive normal form (CNF) in contrast to the disjunctive normal form (DNF). We demonstrate on PubMed author records that CNF blocking reduces more pairs while preserving high pairs completeness compared to the previous methods that use a DNF and that the computation time is significantly reduced. In addition, we also show how to ensure that the method produces disjoint blocks so that much of the AND algorithm can be efficiently paralleled. Our CNF blocking method is tested on the entire PubMed database of 80 million author mentions and efficiently removes 82.17% of all author record pairs in 10 minutes.
%R 10.18653/v1/2020.sdp-1.8
%U https://aclanthology.org/2020.sdp-1.8/
%U https://doi.org/10.18653/v1/2020.sdp-1.8
%P 72-80
Markdown (Informal)
[Learning CNF Blocking for Large-scale Author Name Disambiguation](https://aclanthology.org/2020.sdp-1.8/) (Kim et al., sdp 2020)
ACL