@inproceedings{mutlu-hurriyetoglu-2023-negative,
title = "Negative documents are positive: Improving event extraction performance using overlooked negative data",
author = {Mutlu, Osman and
H{\"u}rriyeto{\u{g}}lu, Ali},
editor = {H{\"u}rriyeto{\u{g}}lu, Ali and
Tanev, Hristo and
Zavarella, Vanni and
Yeniterzi, Reyyan and
Y{\"o}r{\"u}k, Erdem and
Slavcheva, Milena},
booktitle = "Proceedings of the 6th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text",
month = sep,
year = "2023",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2023.case-1.17",
pages = "124--135",
abstract = "The scarcity of data poses a significant challenge in closed-domain event extraction, as is common in complex NLP tasks. This limitation primarily arises from the intricate nature of the annotation process. To address this issue, we present a multi-task model structure and training approach that leverages the additional data, which is found as not having any event information at document and sentence levels, generated during the event annotation process. By incorporating this supplementary data, our proposed framework demonstrates enhanced robustness and, in some scenarios, improved performance. A particularly noteworthy observation is that including only negative documents in addition to the original data contributes to performance enhancement. Our findings offer promising insights into leveraging extra data to mitigate data scarcity challenges in closed-domain event extraction.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mutlu-hurriyetoglu-2023-negative">
<titleInfo>
<title>Negative documents are positive: Improving event extraction performance using overlooked negative data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Osman</namePart>
<namePart type="family">Mutlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Hürriyetoğlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Hürriyetoğlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hristo</namePart>
<namePart type="family">Tanev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vanni</namePart>
<namePart type="family">Zavarella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reyyan</namePart>
<namePart type="family">Yeniterzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erdem</namePart>
<namePart type="family">Yörük</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Milena</namePart>
<namePart type="family">Slavcheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The scarcity of data poses a significant challenge in closed-domain event extraction, as is common in complex NLP tasks. This limitation primarily arises from the intricate nature of the annotation process. To address this issue, we present a multi-task model structure and training approach that leverages the additional data, which is found as not having any event information at document and sentence levels, generated during the event annotation process. By incorporating this supplementary data, our proposed framework demonstrates enhanced robustness and, in some scenarios, improved performance. A particularly noteworthy observation is that including only negative documents in addition to the original data contributes to performance enhancement. Our findings offer promising insights into leveraging extra data to mitigate data scarcity challenges in closed-domain event extraction.</abstract>
<identifier type="citekey">mutlu-hurriyetoglu-2023-negative</identifier>
<location>
<url>https://aclanthology.org/2023.case-1.17</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>124</start>
<end>135</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Negative documents are positive: Improving event extraction performance using overlooked negative data
%A Mutlu, Osman
%A Hürriyetoğlu, Ali
%Y Hürriyetoğlu, Ali
%Y Tanev, Hristo
%Y Zavarella, Vanni
%Y Yeniterzi, Reyyan
%Y Yörük, Erdem
%Y Slavcheva, Milena
%S Proceedings of the 6th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text
%D 2023
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F mutlu-hurriyetoglu-2023-negative
%X The scarcity of data poses a significant challenge in closed-domain event extraction, as is common in complex NLP tasks. This limitation primarily arises from the intricate nature of the annotation process. To address this issue, we present a multi-task model structure and training approach that leverages the additional data, which is found as not having any event information at document and sentence levels, generated during the event annotation process. By incorporating this supplementary data, our proposed framework demonstrates enhanced robustness and, in some scenarios, improved performance. A particularly noteworthy observation is that including only negative documents in addition to the original data contributes to performance enhancement. Our findings offer promising insights into leveraging extra data to mitigate data scarcity challenges in closed-domain event extraction.
%U https://aclanthology.org/2023.case-1.17
%P 124-135
Markdown (Informal)
[Negative documents are positive: Improving event extraction performance using overlooked negative data](https://aclanthology.org/2023.case-1.17) (Mutlu & Hürriyetoğlu, CASE-WS 2023)
ACL