@inproceedings{hurriyetoglu-etal-2020-covcor20,
title = "{COVCOR}20 at {WNUT}-2020 Task 2: An Attempt to Combine Deep Learning and Expert rules",
author = {H{\"u}rriyeto{\u{g}}lu, Ali and
Safaya, Ali and
Mutlu, Osman and
Oostdijk, Nelleke and
Y{\"o}r{\"u}k, Erdem},
booktitle = "Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wnut-1.75",
doi = "10.18653/v1/2020.wnut-1.75",
pages = "495--498",
abstract = "In the scope of WNUT-2020 Task 2, we developed various text classification systems, using deep learning models and one using linguistically informed rules. While both of the deep learning systems outperformed the system using the linguistically informed rules, we found that through the integration of (the output of) the three systems a better performance could be achieved than the standalone performance of each approach in a cross-validation setting. However, on the test data the performance of the integration was slightly lower than our best performing deep learning model. These results hardly indicate any progress in line of integrating machine learning and expert rules driven systems. We expect that the release of the annotation manuals and gold labels of the test data after this workshop will shed light on these perplexing results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hurriyetoglu-etal-2020-covcor20">
<titleInfo>
<title>COVCOR20 at WNUT-2020 Task 2: An Attempt to Combine Deep Learning and Expert rules</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Hürriyetoğlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Safaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Nelleke</namePart>
<namePart type="family">Oostdijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erdem</namePart>
<namePart type="family">Yörük</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the scope of WNUT-2020 Task 2, we developed various text classification systems, using deep learning models and one using linguistically informed rules. While both of the deep learning systems outperformed the system using the linguistically informed rules, we found that through the integration of (the output of) the three systems a better performance could be achieved than the standalone performance of each approach in a cross-validation setting. However, on the test data the performance of the integration was slightly lower than our best performing deep learning model. These results hardly indicate any progress in line of integrating machine learning and expert rules driven systems. We expect that the release of the annotation manuals and gold labels of the test data after this workshop will shed light on these perplexing results.</abstract>
<identifier type="citekey">hurriyetoglu-etal-2020-covcor20</identifier>
<identifier type="doi">10.18653/v1/2020.wnut-1.75</identifier>
<location>
<url>https://aclanthology.org/2020.wnut-1.75</url>
</location>
<part>
<date>2020-nov</date>
<extent unit="page">
<start>495</start>
<end>498</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T COVCOR20 at WNUT-2020 Task 2: An Attempt to Combine Deep Learning and Expert rules
%A Hürriyetoğlu, Ali
%A Safaya, Ali
%A Mutlu, Osman
%A Oostdijk, Nelleke
%A Yörük, Erdem
%S Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)
%D 2020
%8 nov
%I Association for Computational Linguistics
%C Online
%F hurriyetoglu-etal-2020-covcor20
%X In the scope of WNUT-2020 Task 2, we developed various text classification systems, using deep learning models and one using linguistically informed rules. While both of the deep learning systems outperformed the system using the linguistically informed rules, we found that through the integration of (the output of) the three systems a better performance could be achieved than the standalone performance of each approach in a cross-validation setting. However, on the test data the performance of the integration was slightly lower than our best performing deep learning model. These results hardly indicate any progress in line of integrating machine learning and expert rules driven systems. We expect that the release of the annotation manuals and gold labels of the test data after this workshop will shed light on these perplexing results.
%R 10.18653/v1/2020.wnut-1.75
%U https://aclanthology.org/2020.wnut-1.75
%U https://doi.org/10.18653/v1/2020.wnut-1.75
%P 495-498
Markdown (Informal)
[COVCOR20 at WNUT-2020 Task 2: An Attempt to Combine Deep Learning and Expert rules](https://aclanthology.org/2020.wnut-1.75) (Hürriyetoğlu et al., WNUT 2020)
ACL