@inproceedings{aumiller-etal-2020-unihd,
title = "{U}ni{HD}@{CL}-{S}ci{S}umm 2020: Citation Extraction as Search",
author = "Aumiller, Dennis and
Almasian, Satya and
Hausner, Philip and
Gertz, Michael",
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-1.29",
doi = "10.18653/v1/2020.sdp-1.29",
pages = "261--269",
abstract = "This work presents the entry by the team from Heidelberg University in the CL-SciSumm 2020 shared task at the Scholarly Document Processing workshop at EMNLP 2020. As in its previous iterations, the task is to highlight relevant parts in a reference paper, depending on a citance text excerpt from a citing paper. We participated in tasks 1A (citation identification) and 1B (citation context classification). Contrary to most previous works, we frame Task 1A as a search relevance problem, and introduce a 2-step re-ranking approach, which consists of a preselection based on BM25 in addition to positional document features, and a top-k re-ranking with BERT. For Task 1B, we follow previous submissions in applying methods that deal well with low resources and imbalanced classes.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aumiller-etal-2020-unihd">
<titleInfo>
<title>UniHD@CL-SciSumm 2020: Citation Extraction as Search</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dennis</namePart>
<namePart type="family">Aumiller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satya</namePart>
<namePart type="family">Almasian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philip</namePart>
<namePart type="family">Hausner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Gertz</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>This work presents the entry by the team from Heidelberg University in the CL-SciSumm 2020 shared task at the Scholarly Document Processing workshop at EMNLP 2020. As in its previous iterations, the task is to highlight relevant parts in a reference paper, depending on a citance text excerpt from a citing paper. We participated in tasks 1A (citation identification) and 1B (citation context classification). Contrary to most previous works, we frame Task 1A as a search relevance problem, and introduce a 2-step re-ranking approach, which consists of a preselection based on BM25 in addition to positional document features, and a top-k re-ranking with BERT. For Task 1B, we follow previous submissions in applying methods that deal well with low resources and imbalanced classes.</abstract>
<identifier type="citekey">aumiller-etal-2020-unihd</identifier>
<identifier type="doi">10.18653/v1/2020.sdp-1.29</identifier>
<location>
<url>https://aclanthology.org/2020.sdp-1.29</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>261</start>
<end>269</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UniHD@CL-SciSumm 2020: Citation Extraction as Search
%A Aumiller, Dennis
%A Almasian, Satya
%A Hausner, Philip
%A Gertz, Michael
%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 aumiller-etal-2020-unihd
%X This work presents the entry by the team from Heidelberg University in the CL-SciSumm 2020 shared task at the Scholarly Document Processing workshop at EMNLP 2020. As in its previous iterations, the task is to highlight relevant parts in a reference paper, depending on a citance text excerpt from a citing paper. We participated in tasks 1A (citation identification) and 1B (citation context classification). Contrary to most previous works, we frame Task 1A as a search relevance problem, and introduce a 2-step re-ranking approach, which consists of a preselection based on BM25 in addition to positional document features, and a top-k re-ranking with BERT. For Task 1B, we follow previous submissions in applying methods that deal well with low resources and imbalanced classes.
%R 10.18653/v1/2020.sdp-1.29
%U https://aclanthology.org/2020.sdp-1.29
%U https://doi.org/10.18653/v1/2020.sdp-1.29
%P 261-269
Markdown (Informal)
[UniHD@CL-SciSumm 2020: Citation Extraction as Search](https://aclanthology.org/2020.sdp-1.29) (Aumiller et al., sdp 2020)
ACL
- Dennis Aumiller, Satya Almasian, Philip Hausner, and Michael Gertz. 2020. UniHD@CL-SciSumm 2020: Citation Extraction as Search. In Proceedings of the First Workshop on Scholarly Document Processing, pages 261–269, Online. Association for Computational Linguistics.