@inproceedings{bikaun-etal-2021-lexiclean,
title = "{L}exi{C}lean: An annotation tool for rapid multi-task lexical normalisation",
author = "Bikaun, Tyler and
French, Tim and
Hodkiewicz, Melinda and
Stewart, Michael and
Liu, Wei",
editor = "Adel, Heike and
Shi, Shuming",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-demo.25",
doi = "10.18653/v1/2021.emnlp-demo.25",
pages = "212--219",
abstract = "NLP systems are often challenged by difficulties arising from noisy, non-standard, and domain specific corpora. The task of lexical normalisation aims to standardise such corpora, but currently lacks suitable tools to acquire high-quality annotated data to support deep learning based approaches. In this paper, we present LexiClean, the first open-source web-based annotation tool for multi-task lexical normalisation. LexiClean{'}s main contribution is support for simultaneous in situ token-level modification and annotation that can be rapidly applied corpus wide. We demonstrate the usefulness of our tool through a case study on two sets of noisy corpora derived from the specialised-domain of industrial mining. We show that LexiClean allows for the rapid and efficient development of high-quality parallel corpora. A demo of our system is available at: \url{https://youtu.be/P7_ooKrQPDU}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bikaun-etal-2021-lexiclean">
<titleInfo>
<title>LexiClean: An annotation tool for rapid multi-task lexical normalisation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tyler</namePart>
<namePart type="family">Bikaun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">French</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Melinda</namePart>
<namePart type="family">Hodkiewicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Stewart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Heike</namePart>
<namePart type="family">Adel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuming</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>NLP systems are often challenged by difficulties arising from noisy, non-standard, and domain specific corpora. The task of lexical normalisation aims to standardise such corpora, but currently lacks suitable tools to acquire high-quality annotated data to support deep learning based approaches. In this paper, we present LexiClean, the first open-source web-based annotation tool for multi-task lexical normalisation. LexiClean’s main contribution is support for simultaneous in situ token-level modification and annotation that can be rapidly applied corpus wide. We demonstrate the usefulness of our tool through a case study on two sets of noisy corpora derived from the specialised-domain of industrial mining. We show that LexiClean allows for the rapid and efficient development of high-quality parallel corpora. A demo of our system is available at: https://youtu.be/P7_ooKrQPDU.</abstract>
<identifier type="citekey">bikaun-etal-2021-lexiclean</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-demo.25</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-demo.25</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>212</start>
<end>219</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LexiClean: An annotation tool for rapid multi-task lexical normalisation
%A Bikaun, Tyler
%A French, Tim
%A Hodkiewicz, Melinda
%A Stewart, Michael
%A Liu, Wei
%Y Adel, Heike
%Y Shi, Shuming
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F bikaun-etal-2021-lexiclean
%X NLP systems are often challenged by difficulties arising from noisy, non-standard, and domain specific corpora. The task of lexical normalisation aims to standardise such corpora, but currently lacks suitable tools to acquire high-quality annotated data to support deep learning based approaches. In this paper, we present LexiClean, the first open-source web-based annotation tool for multi-task lexical normalisation. LexiClean’s main contribution is support for simultaneous in situ token-level modification and annotation that can be rapidly applied corpus wide. We demonstrate the usefulness of our tool through a case study on two sets of noisy corpora derived from the specialised-domain of industrial mining. We show that LexiClean allows for the rapid and efficient development of high-quality parallel corpora. A demo of our system is available at: https://youtu.be/P7_ooKrQPDU.
%R 10.18653/v1/2021.emnlp-demo.25
%U https://aclanthology.org/2021.emnlp-demo.25
%U https://doi.org/10.18653/v1/2021.emnlp-demo.25
%P 212-219
Markdown (Informal)
[LexiClean: An annotation tool for rapid multi-task lexical normalisation](https://aclanthology.org/2021.emnlp-demo.25) (Bikaun et al., EMNLP 2021)
ACL
- Tyler Bikaun, Tim French, Melinda Hodkiewicz, Michael Stewart, and Wei Liu. 2021. LexiClean: An annotation tool for rapid multi-task lexical normalisation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 212–219, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.