@inproceedings{akhbardeh-etal-2021-handling,
title = "Handling Extreme Class Imbalance in Technical Logbook Datasets",
author = "Akhbardeh, Farhad and
Alm, Cecilia Ovesdotter and
Zampieri, Marcos and
Desell, Travis",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.312",
doi = "10.18653/v1/2021.acl-long.312",
pages = "4034--4045",
abstract = "Technical logbooks are a challenging and under-explored text type in automated event identification. These texts are typically short and written in non-standard yet technical language, posing challenges to off-the-shelf NLP pipelines. The granularity of issue types described in these datasets additionally leads to class imbalance, making it challenging for models to accurately predict which issue each logbook entry describes. In this paper we focus on the problem of technical issue classification by considering logbook datasets from the automotive, aviation, and facilities maintenance domains. We adapt a feedback strategy from computer vision for handling extreme class imbalance, which resamples the training data based on its error in the prediction process. Our experiments show that with statistical significance this feedback strategy provides the best results for four different neural network models trained across a suite of seven different technical logbook datasets from distinct technical domains. The feedback strategy is also generic and could be applied to any learning problem with substantial class imbalances.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="akhbardeh-etal-2021-handling">
<titleInfo>
<title>Handling Extreme Class Imbalance in Technical Logbook Datasets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Farhad</namePart>
<namePart type="family">Akhbardeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cecilia</namePart>
<namePart type="given">Ovesdotter</namePart>
<namePart type="family">Alm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Travis</namePart>
<namePart type="family">Desell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</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>Technical logbooks are a challenging and under-explored text type in automated event identification. These texts are typically short and written in non-standard yet technical language, posing challenges to off-the-shelf NLP pipelines. The granularity of issue types described in these datasets additionally leads to class imbalance, making it challenging for models to accurately predict which issue each logbook entry describes. In this paper we focus on the problem of technical issue classification by considering logbook datasets from the automotive, aviation, and facilities maintenance domains. We adapt a feedback strategy from computer vision for handling extreme class imbalance, which resamples the training data based on its error in the prediction process. Our experiments show that with statistical significance this feedback strategy provides the best results for four different neural network models trained across a suite of seven different technical logbook datasets from distinct technical domains. The feedback strategy is also generic and could be applied to any learning problem with substantial class imbalances.</abstract>
<identifier type="citekey">akhbardeh-etal-2021-handling</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.312</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.312</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>4034</start>
<end>4045</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Handling Extreme Class Imbalance in Technical Logbook Datasets
%A Akhbardeh, Farhad
%A Alm, Cecilia Ovesdotter
%A Zampieri, Marcos
%A Desell, Travis
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F akhbardeh-etal-2021-handling
%X Technical logbooks are a challenging and under-explored text type in automated event identification. These texts are typically short and written in non-standard yet technical language, posing challenges to off-the-shelf NLP pipelines. The granularity of issue types described in these datasets additionally leads to class imbalance, making it challenging for models to accurately predict which issue each logbook entry describes. In this paper we focus on the problem of technical issue classification by considering logbook datasets from the automotive, aviation, and facilities maintenance domains. We adapt a feedback strategy from computer vision for handling extreme class imbalance, which resamples the training data based on its error in the prediction process. Our experiments show that with statistical significance this feedback strategy provides the best results for four different neural network models trained across a suite of seven different technical logbook datasets from distinct technical domains. The feedback strategy is also generic and could be applied to any learning problem with substantial class imbalances.
%R 10.18653/v1/2021.acl-long.312
%U https://aclanthology.org/2021.acl-long.312
%U https://doi.org/10.18653/v1/2021.acl-long.312
%P 4034-4045
Markdown (Informal)
[Handling Extreme Class Imbalance in Technical Logbook Datasets](https://aclanthology.org/2021.acl-long.312) (Akhbardeh et al., ACL-IJCNLP 2021)
ACL
- Farhad Akhbardeh, Cecilia Ovesdotter Alm, Marcos Zampieri, and Travis Desell. 2021. Handling Extreme Class Imbalance in Technical Logbook Datasets. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 4034–4045, Online. Association for Computational Linguistics.