Evaluating Ensembled Transformers for Multilingual Code-Switched Sentiment Analysis

被引:0
|
作者
Aryal, Saurav K. [1 ]
Prioleau, Howard [1 ]
Washington, Gloria [1 ]
Burge, Legand [1 ]
机构
[1] Howard Univ, Comp Sci, Washington, DC 20059 USA
来源
2023 INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE AND COMPUTATIONAL INTELLIGENCE, CSCI 2023 | 2023年
基金
美国国家卫生研究院;
关键词
Code Switching; Ensembling; BERT; Transformers;
D O I
10.1109/CSCI62032.2023.00032
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Sentiment analysis is essential for understanding human-authored texts, especially in multilingual communities where code-switching is common. Most existing research focuses on single-language pair sentiment analysis. We introduce a three-step approach for sentiment analysis on code-switched data: translating the code-switched data into English at word and sentence levels, training on Transformer models, and utilizing a stacking classifier to ensemble the models for sentiment classification. We establish a performance benchmark for binary and ternary sentiment classification by applying this to five datasets featuring English mixed with Spanish, Tamil, Telugu, Hindi, and Malayalam. Our method emphasizes the potential of ensembled Transformer models in this domain, paving the way for future advancements.
引用
收藏
页码:165 / 173
页数:9
相关论文
共 50 条
  • [11] Machine Translation on a Parallel Code-Switched Corpus
    Menacer, M. A.
    Langlois, D.
    Jouvet, D.
    Fohr, D.
    Mella, O.
    Smaili, K.
    ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, 11489 : 426 - 432
  • [12] Sentiment Analysis for Egyptian Arabic-English Code-Switched Data Using Traditional Neural Models and Advanced Language Models
    Sherif, Ahmed
    Sabty, Caroline
    SPEECH AND COMPUTER, SPECOM 2024, PT II, 2025, 15300 : 54 - 69
  • [13] TRANSFORMER-TRANSDUCERS FOR CODE-SWITCHED SPEECH RECOGNITION
    Dalmia, Siddharth
    Liu, Yuzong
    Ronanki, Srikanth
    Kirchhoff, Katrin
    2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 5859 - 5863
  • [14] An Algerian Arabic-French Code-Switched Corpus
    Cotterell, Ryan
    Renduchintala, Adithya
    Saphra, Naomi
    Callison-Burch, Chris
    LREC 2014 - NINTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION, 2014,
  • [15] Code-Switched Advertisements in the Non-Bilingual Community
    Wang, Yunqi
    PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON SMALL AND MEDIUM-SIZED ENTERPRISES (SMES) PSYCHOLOGICAL ADAPTATION AND SOCIAL BEHAVIOR UNDER FINANCIAL CRISIS, 2010, : 323 - 327
  • [16] Multilingual Neural Network Acoustic Modelling for ASR of Under-Resourced English-isiZulu Code-Switched Speech
    Biswas, Astik
    de Wet, Febe
    van der Westhuizen, Ewald
    Yzlmaz, Emre
    Niesler, Thomas
    19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 2603 - 2607
  • [17] Homophone Identification and Merging for Code-switched Speech Recognition
    Srivastava, Brij Mohan Lal
    Sitara, Sunayana
    19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 1943 - 1947
  • [18] Collecting Code-Switched Data from Social Media
    Mendels, Gideon
    Soto, Victor
    Jaech, Aaron
    Hirschberg, Julia
    PROCEEDINGS OF THE ELEVENTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION (LREC 2018), 2018, : 671 - 678
  • [19] An Arabic-Moroccan Darija Code-Switched Corpus
    Samih, Younes
    Maier, Wolfgang
    LREC 2016 - TENTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION, 2016, : 4170 - 4175
  • [20] Adapter-based fine-tuning of pre-trained multilingual language models for code-mixed and code-switched text classification
    Himashi Rathnayake
    Janani Sumanapala
    Raveesha Rukshani
    Surangika Ranathunga
    Knowledge and Information Systems, 2022, 64 : 1937 - 1966