@inproceedings{ayman-etal-2024-bengalilcp-dataset,
title = "{B}engali{LCP}: A Dataset for Lexical Complexity Prediction in the {B}engali Texts",
author = "Ayman, Nabila and
Hossain, Md. Akram and
Aziz, Abdul and
Faruqui, Rokan Uddin and
Chy, Abu Nowshed",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.200",
pages = "2227--2237",
abstract = "Encountering intricate or ambiguous terms within a sentence produces distress for the reader during comprehension. Lexical Complexity Prediction (LCP) deals with predicting the complexity score of a word or a phrase considering its context. This task poses several challenges including ambiguity, context sensitivity, and subjectivity in perceiving complexity. Despite having 300 million native speakers and ranking as the seventh most spoken language in the world, Bengali falls behind in the research on lexical complexity when compared to other languages. To bridge this gap, we introduce the first annotated Bengali dataset, that assists in performing the task of LCP in this language. Besides, we propose a transformer-based deep neural approach with a pairwise multi-head attention mechanism and LSTM model to predict the lexical complexity of Bengali tokens. The outcomes demonstrate that the proposed neural approach outperformed the existing state-of-the-art models for the Bengali language.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ayman-etal-2024-bengalilcp-dataset">
<titleInfo>
<title>BengaliLCP: A Dataset for Lexical Complexity Prediction in the Bengali Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nabila</namePart>
<namePart type="family">Ayman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Akram</namePart>
<namePart type="family">Hossain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdul</namePart>
<namePart type="family">Aziz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rokan</namePart>
<namePart type="given">Uddin</namePart>
<namePart type="family">Faruqui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abu</namePart>
<namePart type="given">Nowshed</namePart>
<namePart type="family">Chy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Encountering intricate or ambiguous terms within a sentence produces distress for the reader during comprehension. Lexical Complexity Prediction (LCP) deals with predicting the complexity score of a word or a phrase considering its context. This task poses several challenges including ambiguity, context sensitivity, and subjectivity in perceiving complexity. Despite having 300 million native speakers and ranking as the seventh most spoken language in the world, Bengali falls behind in the research on lexical complexity when compared to other languages. To bridge this gap, we introduce the first annotated Bengali dataset, that assists in performing the task of LCP in this language. Besides, we propose a transformer-based deep neural approach with a pairwise multi-head attention mechanism and LSTM model to predict the lexical complexity of Bengali tokens. The outcomes demonstrate that the proposed neural approach outperformed the existing state-of-the-art models for the Bengali language.</abstract>
<identifier type="citekey">ayman-etal-2024-bengalilcp-dataset</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.200</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>2227</start>
<end>2237</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BengaliLCP: A Dataset for Lexical Complexity Prediction in the Bengali Texts
%A Ayman, Nabila
%A Hossain, Md. Akram
%A Aziz, Abdul
%A Faruqui, Rokan Uddin
%A Chy, Abu Nowshed
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F ayman-etal-2024-bengalilcp-dataset
%X Encountering intricate or ambiguous terms within a sentence produces distress for the reader during comprehension. Lexical Complexity Prediction (LCP) deals with predicting the complexity score of a word or a phrase considering its context. This task poses several challenges including ambiguity, context sensitivity, and subjectivity in perceiving complexity. Despite having 300 million native speakers and ranking as the seventh most spoken language in the world, Bengali falls behind in the research on lexical complexity when compared to other languages. To bridge this gap, we introduce the first annotated Bengali dataset, that assists in performing the task of LCP in this language. Besides, we propose a transformer-based deep neural approach with a pairwise multi-head attention mechanism and LSTM model to predict the lexical complexity of Bengali tokens. The outcomes demonstrate that the proposed neural approach outperformed the existing state-of-the-art models for the Bengali language.
%U https://aclanthology.org/2024.lrec-main.200
%P 2227-2237
Markdown (Informal)
[BengaliLCP: A Dataset for Lexical Complexity Prediction in the Bengali Texts](https://aclanthology.org/2024.lrec-main.200) (Ayman et al., LREC-COLING 2024)
ACL