@inproceedings{man-duc-trong-etal-2020-introducing,
title = "Introducing a New Dataset for Event Detection in Cybersecurity Texts",
author = "Man Duc Trong, Hieu and
Trong Le, Duc and
Pouran Ben Veyseh, Amir and
Nguyen, Thuat and
Nguyen, Thien Huu",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.433",
doi = "10.18653/v1/2020.emnlp-main.433",
pages = "5381--5390",
abstract = "Detecting cybersecurity events is necessary to keep us informed about the fast growing number of such events reported in text. In this work, we focus on the task of event detection (ED) to identify event trigger words for the cybersecurity domain. In particular, to facilitate the future research, we introduce a new dataset for this problem, characterizing the manual annotation for 30 important cybersecurity event types and a large dataset size to develop deep learning models. Comparing to the prior datasets for this task, our dataset involves more event types and supports the modeling of document-level information to improve the performance. We perform extensive evaluation with the current state-of-the-art methods for ED on the proposed dataset. Our experiments reveal the challenges of cybersecurity ED and present many research opportunities in this area for the future work.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="man-duc-trong-etal-2020-introducing">
<titleInfo>
<title>Introducing a New Dataset for Event Detection in Cybersecurity Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hieu</namePart>
<namePart type="family">Man Duc Trong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Duc</namePart>
<namePart type="family">Trong Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Pouran Ben Veyseh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thuat</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thien</namePart>
<namePart type="given">Huu</namePart>
<namePart type="family">Nguyen</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 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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>Detecting cybersecurity events is necessary to keep us informed about the fast growing number of such events reported in text. In this work, we focus on the task of event detection (ED) to identify event trigger words for the cybersecurity domain. In particular, to facilitate the future research, we introduce a new dataset for this problem, characterizing the manual annotation for 30 important cybersecurity event types and a large dataset size to develop deep learning models. Comparing to the prior datasets for this task, our dataset involves more event types and supports the modeling of document-level information to improve the performance. We perform extensive evaluation with the current state-of-the-art methods for ED on the proposed dataset. Our experiments reveal the challenges of cybersecurity ED and present many research opportunities in this area for the future work.</abstract>
<identifier type="citekey">man-duc-trong-etal-2020-introducing</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.433</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.433</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>5381</start>
<end>5390</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Introducing a New Dataset for Event Detection in Cybersecurity Texts
%A Man Duc Trong, Hieu
%A Trong Le, Duc
%A Pouran Ben Veyseh, Amir
%A Nguyen, Thuat
%A Nguyen, Thien Huu
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F man-duc-trong-etal-2020-introducing
%X Detecting cybersecurity events is necessary to keep us informed about the fast growing number of such events reported in text. In this work, we focus on the task of event detection (ED) to identify event trigger words for the cybersecurity domain. In particular, to facilitate the future research, we introduce a new dataset for this problem, characterizing the manual annotation for 30 important cybersecurity event types and a large dataset size to develop deep learning models. Comparing to the prior datasets for this task, our dataset involves more event types and supports the modeling of document-level information to improve the performance. We perform extensive evaluation with the current state-of-the-art methods for ED on the proposed dataset. Our experiments reveal the challenges of cybersecurity ED and present many research opportunities in this area for the future work.
%R 10.18653/v1/2020.emnlp-main.433
%U https://aclanthology.org/2020.emnlp-main.433
%U https://doi.org/10.18653/v1/2020.emnlp-main.433
%P 5381-5390
Markdown (Informal)
[Introducing a New Dataset for Event Detection in Cybersecurity Texts](https://aclanthology.org/2020.emnlp-main.433) (Man Duc Trong et al., EMNLP 2020)
ACL