@inproceedings{hovelmeyer-kartal-2022-varanalysis,
title = "Varanalysis@{SV}-Ident 2022: Variable Detection and Disambiguation Based on Semantic Similarity",
author = {H{\"o}velmeyer, Alica and
Kartal, Yavuz Selim},
editor = "Cohan, Arman and
Feigenblat, Guy and
Freitag, Dayne and
Ghosal, Tirthankar and
Herrmannova, Drahomira and
Knoth, Petr and
Lo, Kyle and
Mayr, Philipp and
Shmueli-Scheuer, Michal and
de Waard, Anita and
Wang, Lucy Lu",
booktitle = "Proceedings of the Third Workshop on Scholarly Document Processing",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.sdp-1.30",
pages = "247--252",
abstract = "This paper describes an approach to the SV-Ident Shared Task which requires the detection and disambiguation of survey variables in sentences taken from social science publications. It deals with both subtasks as problems of semantic textual similarity (STS) and relies on the use of sentence transformers. Sentences and variables are examined for semantic similarity for both detecting sentences containing variables and disambiguating the respective variables. The focus is placed on analyzing the effects of including different parts of the variables and observing the differences between English and German instances. Additionally, for the variable detection task a bag of words model is used to filter out sentences which are likely to contain a variable mention as a preselection of sentences to perform the semantic similarity comparison on.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hovelmeyer-kartal-2022-varanalysis">
<titleInfo>
<title>Varanalysis@SV-Ident 2022: Variable Detection and Disambiguation Based on Semantic Similarity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alica</namePart>
<namePart type="family">Hövelmeyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yavuz</namePart>
<namePart type="given">Selim</namePart>
<namePart type="family">Kartal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Scholarly Document Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arman</namePart>
<namePart type="family">Cohan</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">Drahomira</namePart>
<namePart type="family">Herrmannova</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">Kyle</namePart>
<namePart type="family">Lo</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">Michal</namePart>
<namePart type="family">Shmueli-Scheuer</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">Lucy</namePart>
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes an approach to the SV-Ident Shared Task which requires the detection and disambiguation of survey variables in sentences taken from social science publications. It deals with both subtasks as problems of semantic textual similarity (STS) and relies on the use of sentence transformers. Sentences and variables are examined for semantic similarity for both detecting sentences containing variables and disambiguating the respective variables. The focus is placed on analyzing the effects of including different parts of the variables and observing the differences between English and German instances. Additionally, for the variable detection task a bag of words model is used to filter out sentences which are likely to contain a variable mention as a preselection of sentences to perform the semantic similarity comparison on.</abstract>
<identifier type="citekey">hovelmeyer-kartal-2022-varanalysis</identifier>
<location>
<url>https://aclanthology.org/2022.sdp-1.30</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>247</start>
<end>252</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Varanalysis@SV-Ident 2022: Variable Detection and Disambiguation Based on Semantic Similarity
%A Hövelmeyer, Alica
%A Kartal, Yavuz Selim
%Y Cohan, Arman
%Y Feigenblat, Guy
%Y Freitag, Dayne
%Y Ghosal, Tirthankar
%Y Herrmannova, Drahomira
%Y Knoth, Petr
%Y Lo, Kyle
%Y Mayr, Philipp
%Y Shmueli-Scheuer, Michal
%Y de Waard, Anita
%Y Wang, Lucy Lu
%S Proceedings of the Third Workshop on Scholarly Document Processing
%D 2022
%8 October
%I Association for Computational Linguistics
%C Gyeongju, Republic of Korea
%F hovelmeyer-kartal-2022-varanalysis
%X This paper describes an approach to the SV-Ident Shared Task which requires the detection and disambiguation of survey variables in sentences taken from social science publications. It deals with both subtasks as problems of semantic textual similarity (STS) and relies on the use of sentence transformers. Sentences and variables are examined for semantic similarity for both detecting sentences containing variables and disambiguating the respective variables. The focus is placed on analyzing the effects of including different parts of the variables and observing the differences between English and German instances. Additionally, for the variable detection task a bag of words model is used to filter out sentences which are likely to contain a variable mention as a preselection of sentences to perform the semantic similarity comparison on.
%U https://aclanthology.org/2022.sdp-1.30
%P 247-252
Markdown (Informal)
[Varanalysis@SV-Ident 2022: Variable Detection and Disambiguation Based on Semantic Similarity](https://aclanthology.org/2022.sdp-1.30) (Hövelmeyer & Kartal, sdp 2022)
ACL