@inproceedings{rahman-etal-2023-bspell,
title = "{BS}pell: A {CNN}-Blended {BERT} Based {B}angla Spell Checker",
author = "Rahman, Chowdhury and
Rahman, MD.Hasibur and
Zakir, Samiha and
Rafsan, Mohammad and
Ali, Mohammed Eunus",
editor = "Alam, Firoj and
Kar, Sudipta and
Chowdhury, Shammur Absar and
Sadeque, Farig and
Amin, Ruhul",
booktitle = "Proceedings of the First Workshop on Bangla Language Processing (BLP-2023)",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.banglalp-1.2",
doi = "10.18653/v1/2023.banglalp-1.2",
pages = "7--17",
abstract = "Bangla typing is mostly performed using English keyboard and can be highly erroneous due to the presence of compound and similarly pronounced letters. Spelling correction of a misspelled word requires understanding of word typing pattern as well as the context of the word usage. A specialized BERT model named BSpell has been proposed in this paper targeted towards word for word correction in sentence level. BSpell contains an end-to-end trainable CNN sub-model named SemanticNet along with specialized auxiliary loss. This allows BSpell to specialize in highly inflected Bangla vocabulary in the presence of spelling errors. Furthermore, a hybrid pretraining scheme has been proposed for BSpell that combines word level and character level masking. Comparison on two Bangla and one Hindi spelling correction dataset shows the superiority of our proposed approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rahman-etal-2023-bspell">
<titleInfo>
<title>BSpell: A CNN-Blended BERT Based Bangla Spell Checker</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chowdhury</namePart>
<namePart type="family">Rahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">MD.Hasibur</namePart>
<namePart type="family">Rahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samiha</namePart>
<namePart type="family">Zakir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">Rafsan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="given">Eunus</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Bangla Language Processing (BLP-2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Firoj</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sudipta</namePart>
<namePart type="family">Kar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shammur</namePart>
<namePart type="given">Absar</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Farig</namePart>
<namePart type="family">Sadeque</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruhul</namePart>
<namePart type="family">Amin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Bangla typing is mostly performed using English keyboard and can be highly erroneous due to the presence of compound and similarly pronounced letters. Spelling correction of a misspelled word requires understanding of word typing pattern as well as the context of the word usage. A specialized BERT model named BSpell has been proposed in this paper targeted towards word for word correction in sentence level. BSpell contains an end-to-end trainable CNN sub-model named SemanticNet along with specialized auxiliary loss. This allows BSpell to specialize in highly inflected Bangla vocabulary in the presence of spelling errors. Furthermore, a hybrid pretraining scheme has been proposed for BSpell that combines word level and character level masking. Comparison on two Bangla and one Hindi spelling correction dataset shows the superiority of our proposed approach.</abstract>
<identifier type="citekey">rahman-etal-2023-bspell</identifier>
<identifier type="doi">10.18653/v1/2023.banglalp-1.2</identifier>
<location>
<url>https://aclanthology.org/2023.banglalp-1.2</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>7</start>
<end>17</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BSpell: A CNN-Blended BERT Based Bangla Spell Checker
%A Rahman, Chowdhury
%A Rahman, MD.Hasibur
%A Zakir, Samiha
%A Rafsan, Mohammad
%A Ali, Mohammed Eunus
%Y Alam, Firoj
%Y Kar, Sudipta
%Y Chowdhury, Shammur Absar
%Y Sadeque, Farig
%Y Amin, Ruhul
%S Proceedings of the First Workshop on Bangla Language Processing (BLP-2023)
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F rahman-etal-2023-bspell
%X Bangla typing is mostly performed using English keyboard and can be highly erroneous due to the presence of compound and similarly pronounced letters. Spelling correction of a misspelled word requires understanding of word typing pattern as well as the context of the word usage. A specialized BERT model named BSpell has been proposed in this paper targeted towards word for word correction in sentence level. BSpell contains an end-to-end trainable CNN sub-model named SemanticNet along with specialized auxiliary loss. This allows BSpell to specialize in highly inflected Bangla vocabulary in the presence of spelling errors. Furthermore, a hybrid pretraining scheme has been proposed for BSpell that combines word level and character level masking. Comparison on two Bangla and one Hindi spelling correction dataset shows the superiority of our proposed approach.
%R 10.18653/v1/2023.banglalp-1.2
%U https://aclanthology.org/2023.banglalp-1.2
%U https://doi.org/10.18653/v1/2023.banglalp-1.2
%P 7-17
Markdown (Informal)
[BSpell: A CNN-Blended BERT Based Bangla Spell Checker](https://aclanthology.org/2023.banglalp-1.2) (Rahman et al., BanglaLP 2023)
ACL
- Chowdhury Rahman, MD.Hasibur Rahman, Samiha Zakir, Mohammad Rafsan, and Mohammed Eunus Ali. 2023. BSpell: A CNN-Blended BERT Based Bangla Spell Checker. In Proceedings of the First Workshop on Bangla Language Processing (BLP-2023), pages 7–17, Singapore. Association for Computational Linguistics.