@inproceedings{kacker-etal-2021-abb,
title = "{ABB}-{BERT}: A {BERT} model for disambiguating abbreviations and contractions",
author = "Kacker, Prateek and
Cupallari, Andi and
Subramanian, Aswin and
Jain, Nimit",
editor = "Bandyopadhyay, Sivaji and
Devi, Sobha Lalitha and
Bhattacharyya, Pushpak",
booktitle = "Proceedings of the 18th International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2021",
address = "National Institute of Technology Silchar, Silchar, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2021.icon-main.35",
pages = "289--297",
abstract = "Abbreviations and contractions are commonly found in text across different domains. For example, doctors{'} notes contain many contractions that can be personalized based on their choices. Existing spelling correction models are not suitable to handle expansions because of many reductions of characters in words. In this work, we propose ABB-BERT, a BERT-based model, which deals with an ambiguous language containing abbreviations and contractions. ABB-BERT can rank them from thousands of options and is designed for scale. It is trained on Wikipedia text, and the algorithm allows it to be fine-tuned with little compute to get better performance for a domain or person. We are publicly releasing the training dataset for abbreviations and contractions derived from Wikipedia.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kacker-etal-2021-abb">
<titleInfo>
<title>ABB-BERT: A BERT model for disambiguating abbreviations and contractions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Prateek</namePart>
<namePart type="family">Kacker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andi</namePart>
<namePart type="family">Cupallari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aswin</namePart>
<namePart type="family">Subramanian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nimit</namePart>
<namePart type="family">Jain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sivaji</namePart>
<namePart type="family">Bandyopadhyay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sobha</namePart>
<namePart type="given">Lalitha</namePart>
<namePart type="family">Devi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">National Institute of Technology Silchar, Silchar, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Abbreviations and contractions are commonly found in text across different domains. For example, doctors’ notes contain many contractions that can be personalized based on their choices. Existing spelling correction models are not suitable to handle expansions because of many reductions of characters in words. In this work, we propose ABB-BERT, a BERT-based model, which deals with an ambiguous language containing abbreviations and contractions. ABB-BERT can rank them from thousands of options and is designed for scale. It is trained on Wikipedia text, and the algorithm allows it to be fine-tuned with little compute to get better performance for a domain or person. We are publicly releasing the training dataset for abbreviations and contractions derived from Wikipedia.</abstract>
<identifier type="citekey">kacker-etal-2021-abb</identifier>
<location>
<url>https://aclanthology.org/2021.icon-main.35</url>
</location>
<part>
<date>2021-12</date>
<extent unit="page">
<start>289</start>
<end>297</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ABB-BERT: A BERT model for disambiguating abbreviations and contractions
%A Kacker, Prateek
%A Cupallari, Andi
%A Subramanian, Aswin
%A Jain, Nimit
%Y Bandyopadhyay, Sivaji
%Y Devi, Sobha Lalitha
%Y Bhattacharyya, Pushpak
%S Proceedings of the 18th International Conference on Natural Language Processing (ICON)
%D 2021
%8 December
%I NLP Association of India (NLPAI)
%C National Institute of Technology Silchar, Silchar, India
%F kacker-etal-2021-abb
%X Abbreviations and contractions are commonly found in text across different domains. For example, doctors’ notes contain many contractions that can be personalized based on their choices. Existing spelling correction models are not suitable to handle expansions because of many reductions of characters in words. In this work, we propose ABB-BERT, a BERT-based model, which deals with an ambiguous language containing abbreviations and contractions. ABB-BERT can rank them from thousands of options and is designed for scale. It is trained on Wikipedia text, and the algorithm allows it to be fine-tuned with little compute to get better performance for a domain or person. We are publicly releasing the training dataset for abbreviations and contractions derived from Wikipedia.
%U https://aclanthology.org/2021.icon-main.35
%P 289-297
Markdown (Informal)
[ABB-BERT: A BERT model for disambiguating abbreviations and contractions](https://aclanthology.org/2021.icon-main.35) (Kacker et al., ICON 2021)
ACL