@inproceedings{liu-etal-2023-knowdee,
title = "Knowdee at {BLP}-2023 Task 2: Improving {B}angla Sentiment Analysis Using Ensembled Models with Pseudo-Labeling",
author = "Liu, Xiaoyi and
Teng, Mao and
Yang, SHuangtao and
Fu, Bo",
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-1.35",
doi = "10.18653/v1/2023.banglalp-1.35",
pages = "273--278",
abstract = "This paper outlines our submission to the Sentiment Analysis Shared Task at the Bangla Language Processing (BLP) Workshop at EMNLP2023 (Hasan et al., 2023a). The objective of this task is to detect sentiment in each text by classifying it as Positive, Negative, or Neutral. This shared task is based on the MUltiplatform BAngla SEntiment (MUBASE) (Hasan et al., 2023b) and SentNob (Islam et al., 2021) dataset, which consists of public comments from various social media platforms. Our proposed method for this task is based on the pre-trained Bangla language model BanglaBERT (Bhattacharjee et al., 2022). We trained an ensemble of BanglaBERT on the original dataset and used it to generate pseudo-labels for data augmentation. This expanded dataset was then used to train our final models. During the evaluation phase, 30 teams submitted their systems, and our system achieved the second highest performance with F1 score of 0.7267. The source code of the proposed approach is available at https://github.com/KnowdeeAI/blp{\_}task2{\_}knowdee.git.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2023-knowdee">
<titleInfo>
<title>Knowdee at BLP-2023 Task 2: Improving Bangla Sentiment Analysis Using Ensembled Models with Pseudo-Labeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaoyi</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mao</namePart>
<namePart type="family">Teng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">SHuangtao</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Fu</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>This paper outlines our submission to the Sentiment Analysis Shared Task at the Bangla Language Processing (BLP) Workshop at EMNLP2023 (Hasan et al., 2023a). The objective of this task is to detect sentiment in each text by classifying it as Positive, Negative, or Neutral. This shared task is based on the MUltiplatform BAngla SEntiment (MUBASE) (Hasan et al., 2023b) and SentNob (Islam et al., 2021) dataset, which consists of public comments from various social media platforms. Our proposed method for this task is based on the pre-trained Bangla language model BanglaBERT (Bhattacharjee et al., 2022). We trained an ensemble of BanglaBERT on the original dataset and used it to generate pseudo-labels for data augmentation. This expanded dataset was then used to train our final models. During the evaluation phase, 30 teams submitted their systems, and our system achieved the second highest performance with F1 score of 0.7267. The source code of the proposed approach is available at https://github.com/KnowdeeAI/blp_task2_knowdee.git.</abstract>
<identifier type="citekey">liu-etal-2023-knowdee</identifier>
<identifier type="doi">10.18653/v1/2023.banglalp-1.35</identifier>
<location>
<url>https://aclanthology.org/2023.banglalp-1.35</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>273</start>
<end>278</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Knowdee at BLP-2023 Task 2: Improving Bangla Sentiment Analysis Using Ensembled Models with Pseudo-Labeling
%A Liu, Xiaoyi
%A Teng, Mao
%A Yang, SHuangtao
%A Fu, Bo
%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 liu-etal-2023-knowdee
%X This paper outlines our submission to the Sentiment Analysis Shared Task at the Bangla Language Processing (BLP) Workshop at EMNLP2023 (Hasan et al., 2023a). The objective of this task is to detect sentiment in each text by classifying it as Positive, Negative, or Neutral. This shared task is based on the MUltiplatform BAngla SEntiment (MUBASE) (Hasan et al., 2023b) and SentNob (Islam et al., 2021) dataset, which consists of public comments from various social media platforms. Our proposed method for this task is based on the pre-trained Bangla language model BanglaBERT (Bhattacharjee et al., 2022). We trained an ensemble of BanglaBERT on the original dataset and used it to generate pseudo-labels for data augmentation. This expanded dataset was then used to train our final models. During the evaluation phase, 30 teams submitted their systems, and our system achieved the second highest performance with F1 score of 0.7267. The source code of the proposed approach is available at https://github.com/KnowdeeAI/blp_task2_knowdee.git.
%R 10.18653/v1/2023.banglalp-1.35
%U https://aclanthology.org/2023.banglalp-1.35
%U https://doi.org/10.18653/v1/2023.banglalp-1.35
%P 273-278
Markdown (Informal)
[Knowdee at BLP-2023 Task 2: Improving Bangla Sentiment Analysis Using Ensembled Models with Pseudo-Labeling](https://aclanthology.org/2023.banglalp-1.35) (Liu et al., BanglaLP 2023)
ACL