Full Description
This book constitutes the refereed conference proceedings of the second International Conference on Speech and Language Technologies for Low-Resource Languages, SPELLL 2023, held in Perundurai, Erode, India, during December 6-8, 2023.
The 27 full papers and 6 short papers presented in this book were carefully reviewed and selected from 94 submissions. The papers are divided into the following topical sections: language resources; language technologies; speech technologies; and workshops - regional fake, MMLOW, LC4.
Contents
.- Language Resources.
.- PolitiKweli: A Swahili-English Code-switched Twitter Political Misinformation Classification Dataset.
.- Telugu Meme Dataset and Baseline System for Automatic Identification of Domain, and Troll in Memes.-
.- SamPar: A Marathi hate speech dataset for Homophobia, Transphobia
.- L3Cube-MahaNews: News-based Short Text and Long Document Classification Datasets in Marathi
.- Creation and Classification of Kannada Meme Dataset: Exploring Domain and Troll Categories
.- Examining the Opportunities in Python Programming.-
.- Language Technologies:
.- Natural Language Processing for Tulu: Challenges, Review and Future Scope.
.- DeepBoost TransNet Transformer Network for Depression Classification.
.- Optimized BERT model for Question Answering System on Mobile Platform.
.- A Comparative Analysis of Pretrained Models for Sentiment Analysis on Restaurant Customer Reviews(CAPM-SARCR)
.- Lightweight Language Agnostic Data Sanitization Pipeline for dealing with Homoglyphs in Code-Mixed Languages
.- TextGram: Towards a better domain-adaptive pretraining
.- Abusive Social Media Comments Detection for Tamil and Telugu
.- Sales Forecasting from Group Conversation using Natural Language Processing
.- Hands in Harmony: Empowering Communication through Translation
.- Offensive text detection for Tamil language.- Telugu-English Abusive Comment Detection using XLMRoBERTa and mBERT
.- A Knowledge Engineering Framework Addressing High Incidence of Farmer Suicides
.- Event Categorization from News Articles using Machine Learning Techniques
.- From Words to Emotions: Identifying Depression through Social Media Insights
.- Text Summarisation for Low-resourced Languages, A review
.- Speech Technologies
.- Multi Speaker Activity Detection Using Spectral Centroids
.- Spoken Language Identification System using Convolutional Neural Networks
.- Exploring the Role of Entropy in Music Classification
.- Spectral Features Based Spoken Dialect Identification for Punjabi Language
.- Hate Speech Detection Using Audio in Portuguese Language
.- An Empirical Analysis of the Consonantal Phonemic Patterns and characteristics of English spoken in India
.- Workshop 1: Workshops - Regional fake, MMLOW, LC4.
.- Multilingual Fake News Detection in Low-Resource Languages: A Comparative Study Using BERT and GPT-3.5
.- Bridging the Language Gap: Transformer-Based BERT for Fake News Detection in Low-Resource Settings
.- Optimized latent-dirichlet-allocation based topic modeling - an empirical study
.- Gender Recognition using ANN and Forward Rajan Transform Inclusive of Transgender Identity
.- Sarcasm Detection for Tamil Code-Mix Data using Transformers
.- Automatic identification of Meimayakkam in Tamil words using Rule based and Transfer learning.
