@inproceedings{roy-etal-2020-learning,
title = "Learning Domain Terms - Empirical Methods to Enhance Enterprise Text Analytics Performance",
author = "Roy, Gargi and
Dey, Lipika and
Shakir, Mohammad and
Dasgupta, Tirthankar",
editor = "Clifton, Ann and
Napoles, Courtney",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics: Industry Track",
month = dec,
year = "2020",
address = "Online",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-industry.18",
doi = "10.18653/v1/2020.coling-industry.18",
pages = "190--201",
abstract = "Performance of standard text analytics algorithms are known to be substantially degraded on consumer generated data, which are often very noisy. These algorithms also do not work well on enterprise data which has a very different nature from News repositories, storybooks or Wikipedia data. Text cleaning is a mandatory step which aims at noise removal and correction to improve performance. However, enterprise data need special cleaning methods since it contains many domain terms which appear to be noise against a standard dictionary, but in reality are not so. In this work we present detailed analysis of characteristics of enterprise data and suggest unsupervised methods for cleaning these repositories after domain terms have been automatically segregated from true noise terms. Noise terms are thereafter corrected in a contextual fashion. The effectiveness of the method is established through careful manual evaluation of error corrections over several standard data sets, including those available for hate speech detection, where there is deliberate distortion to avoid detection. We also share results to show enhancement in classification accuracy after noise correction.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="roy-etal-2020-learning">
<titleInfo>
<title>Learning Domain Terms - Empirical Methods to Enhance Enterprise Text Analytics Performance</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gargi</namePart>
<namePart type="family">Roy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lipika</namePart>
<namePart type="family">Dey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">Shakir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tirthankar</namePart>
<namePart type="family">Dasgupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ann</namePart>
<namePart type="family">Clifton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Courtney</namePart>
<namePart type="family">Napoles</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Performance of standard text analytics algorithms are known to be substantially degraded on consumer generated data, which are often very noisy. These algorithms also do not work well on enterprise data which has a very different nature from News repositories, storybooks or Wikipedia data. Text cleaning is a mandatory step which aims at noise removal and correction to improve performance. However, enterprise data need special cleaning methods since it contains many domain terms which appear to be noise against a standard dictionary, but in reality are not so. In this work we present detailed analysis of characteristics of enterprise data and suggest unsupervised methods for cleaning these repositories after domain terms have been automatically segregated from true noise terms. Noise terms are thereafter corrected in a contextual fashion. The effectiveness of the method is established through careful manual evaluation of error corrections over several standard data sets, including those available for hate speech detection, where there is deliberate distortion to avoid detection. We also share results to show enhancement in classification accuracy after noise correction.</abstract>
<identifier type="citekey">roy-etal-2020-learning</identifier>
<identifier type="doi">10.18653/v1/2020.coling-industry.18</identifier>
<location>
<url>https://aclanthology.org/2020.coling-industry.18</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>190</start>
<end>201</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning Domain Terms - Empirical Methods to Enhance Enterprise Text Analytics Performance
%A Roy, Gargi
%A Dey, Lipika
%A Shakir, Mohammad
%A Dasgupta, Tirthankar
%Y Clifton, Ann
%Y Napoles, Courtney
%S Proceedings of the 28th International Conference on Computational Linguistics: Industry Track
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Online
%F roy-etal-2020-learning
%X Performance of standard text analytics algorithms are known to be substantially degraded on consumer generated data, which are often very noisy. These algorithms also do not work well on enterprise data which has a very different nature from News repositories, storybooks or Wikipedia data. Text cleaning is a mandatory step which aims at noise removal and correction to improve performance. However, enterprise data need special cleaning methods since it contains many domain terms which appear to be noise against a standard dictionary, but in reality are not so. In this work we present detailed analysis of characteristics of enterprise data and suggest unsupervised methods for cleaning these repositories after domain terms have been automatically segregated from true noise terms. Noise terms are thereafter corrected in a contextual fashion. The effectiveness of the method is established through careful manual evaluation of error corrections over several standard data sets, including those available for hate speech detection, where there is deliberate distortion to avoid detection. We also share results to show enhancement in classification accuracy after noise correction.
%R 10.18653/v1/2020.coling-industry.18
%U https://aclanthology.org/2020.coling-industry.18
%U https://doi.org/10.18653/v1/2020.coling-industry.18
%P 190-201
Markdown (Informal)
[Learning Domain Terms - Empirical Methods to Enhance Enterprise Text Analytics Performance](https://aclanthology.org/2020.coling-industry.18) (Roy et al., COLING 2020)
ACL