@inproceedings{afrin-etal-2023-banlemma,
title = "{B}an{L}emma: A Word Formation Dependent Rule and Dictionary Based {B}angla Lemmatizer",
author = "Afrin, Sadia and
Chowdhury, Md. Shahad Mahmud and
Islam, Md. and
Khan, Faisal and
Chowdhury, Labib and
Mahtab, Md. and
Chowdhury, Nazifa and
Forkan, Massud and
Kundu, Neelima and
Arif, Hakim and
Rashid, Mohammad Mamun Or and
Amin, Mohammad and
Mohammed, Nabeel",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.240",
doi = "10.18653/v1/2023.findings-emnlp.240",
pages = "3695--3710",
abstract = "Lemmatization holds significance in both natural language processing (NLP) and linguistics, as it effectively decreases data density and aids in comprehending contextual meaning. However, due to the highly inflected nature and morphological richness, lemmatization in Bangla text poses a complex challenge. In this study, we propose linguistic rules for lemmatization and utilize a dictionary along with the rules to design a lemmatizer specifically for Bangla. Our system aims to lemmatize words based on their parts of speech class within a given sentence. Unlike previous rule-based approaches, we analyzed the suffix marker occurrence according to the morpho-syntactic values and then utilized sequences of suffix markers instead of entire suffixes. To develop our rules, we analyze a large corpus of Bangla text from various domains, sources, and time periods to observe the word formation of inflected words. The lemmatizer achieves an accuracy of 96.36{\%} when tested against a manually annotated test dataset by trained linguists and demonstrates competitive performance on three previously published Bangla lemmatization datasets. We are making the code and datasets publicly available at https://github.com/eblict-gigatech/BanLemma in order to contribute to the further advancement of Bangla NLP.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="afrin-etal-2023-banlemma">
<titleInfo>
<title>BanLemma: A Word Formation Dependent Rule and Dictionary Based Bangla Lemmatizer</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sadia</namePart>
<namePart type="family">Afrin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Shahad</namePart>
<namePart type="given">Mahmud</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="family">Islam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Faisal</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Labib</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="family">Mahtab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nazifa</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Massud</namePart>
<namePart type="family">Forkan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Neelima</namePart>
<namePart type="family">Kundu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hakim</namePart>
<namePart type="family">Arif</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Mamun</namePart>
<namePart type="given">Or</namePart>
<namePart type="family">Rashid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">Amin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nabeel</namePart>
<namePart type="family">Mohammed</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>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</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>Lemmatization holds significance in both natural language processing (NLP) and linguistics, as it effectively decreases data density and aids in comprehending contextual meaning. However, due to the highly inflected nature and morphological richness, lemmatization in Bangla text poses a complex challenge. In this study, we propose linguistic rules for lemmatization and utilize a dictionary along with the rules to design a lemmatizer specifically for Bangla. Our system aims to lemmatize words based on their parts of speech class within a given sentence. Unlike previous rule-based approaches, we analyzed the suffix marker occurrence according to the morpho-syntactic values and then utilized sequences of suffix markers instead of entire suffixes. To develop our rules, we analyze a large corpus of Bangla text from various domains, sources, and time periods to observe the word formation of inflected words. The lemmatizer achieves an accuracy of 96.36% when tested against a manually annotated test dataset by trained linguists and demonstrates competitive performance on three previously published Bangla lemmatization datasets. We are making the code and datasets publicly available at https://github.com/eblict-gigatech/BanLemma in order to contribute to the further advancement of Bangla NLP.</abstract>
<identifier type="citekey">afrin-etal-2023-banlemma</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.240</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.240</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>3695</start>
<end>3710</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BanLemma: A Word Formation Dependent Rule and Dictionary Based Bangla Lemmatizer
%A Afrin, Sadia
%A Chowdhury, Md. Shahad Mahmud
%A Islam, Md.
%A Khan, Faisal
%A Chowdhury, Labib
%A Mahtab, Md.
%A Chowdhury, Nazifa
%A Forkan, Massud
%A Kundu, Neelima
%A Arif, Hakim
%A Rashid, Mohammad Mamun Or
%A Amin, Mohammad
%A Mohammed, Nabeel
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F afrin-etal-2023-banlemma
%X Lemmatization holds significance in both natural language processing (NLP) and linguistics, as it effectively decreases data density and aids in comprehending contextual meaning. However, due to the highly inflected nature and morphological richness, lemmatization in Bangla text poses a complex challenge. In this study, we propose linguistic rules for lemmatization and utilize a dictionary along with the rules to design a lemmatizer specifically for Bangla. Our system aims to lemmatize words based on their parts of speech class within a given sentence. Unlike previous rule-based approaches, we analyzed the suffix marker occurrence according to the morpho-syntactic values and then utilized sequences of suffix markers instead of entire suffixes. To develop our rules, we analyze a large corpus of Bangla text from various domains, sources, and time periods to observe the word formation of inflected words. The lemmatizer achieves an accuracy of 96.36% when tested against a manually annotated test dataset by trained linguists and demonstrates competitive performance on three previously published Bangla lemmatization datasets. We are making the code and datasets publicly available at https://github.com/eblict-gigatech/BanLemma in order to contribute to the further advancement of Bangla NLP.
%R 10.18653/v1/2023.findings-emnlp.240
%U https://aclanthology.org/2023.findings-emnlp.240
%U https://doi.org/10.18653/v1/2023.findings-emnlp.240
%P 3695-3710
Markdown (Informal)
[BanLemma: A Word Formation Dependent Rule and Dictionary Based Bangla Lemmatizer](https://aclanthology.org/2023.findings-emnlp.240) (Afrin et al., Findings 2023)
ACL
- Sadia Afrin, Md. Shahad Mahmud Chowdhury, Md. Islam, Faisal Khan, Labib Chowdhury, Md. Mahtab, Nazifa Chowdhury, Massud Forkan, Neelima Kundu, Hakim Arif, Mohammad Mamun Or Rashid, Mohammad Amin, and Nabeel Mohammed. 2023. BanLemma: A Word Formation Dependent Rule and Dictionary Based Bangla Lemmatizer. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 3695–3710, Singapore. Association for Computational Linguistics.