Titlebook: Speech and Language Technologies for Low-Resource Languages; Second International Bharathi Raja Chakravarthi,Bharathi B,Preslav Nako Confer

NATAL

Creation and Classification of Kannada Meme Dataset: Exploring Domain and Troll Categories memes, spanning various categories such as movies, politics, sports, trolls, and non-troll memes. The classification models have been meticulously fine-tuned for memes, incorporating image-based models using DenseNet169 and text-based models with BERT for text encoding. An innovative multimodal app

Obscure

The Impact of Tamil Python Programming in Wikisourceght-free data. Among these, Wikisource stands out as an online library utilized by 72 languages. Tamil Wikisource specifically caters to Tamil-language content, converting image-based data into text format. While human resources and automated methods contribute to data improvement, this research pap

intelligible

Synapse

DepBoost-TransNet: Boosted Transformer Network for Depression Classificationortance, yet conventional methods, such as self-reporting and professional evaluations, possess inherent limitations and subjectivity. With the proliferation of social media and the abundance of user-generated content, novel approaches employing transformer-based models and text-mining techniques ho

调整校对

简洁

无意

Lightweight Language Agnostic Data Sanitization Pipeline for Dealing with Homoglyphs in Code-Mixed Ltecting hate speech to make social media less toxic. However, hate speech users have started employing homoglyphs, which are characters that look identical to each other but have a different encoding or structure, to evade detection since most NLP models are trained on commonly recognized Unicode ch

Allege

TextGram: Towards a Better Domain-Adaptive Pretrainingaining on Transformer models requires significant computational resources. This pre-training involves using a large amount of text data to gain prior knowledge for performing downstream tasks. Thus, it is important that we select the correct data in the form of domain-specific data from this vast co

euphoria

Abusive Social Media Comments Detection for Tamil and Telugunt from being shared on social media. When it comes to low-resource languages such as Tamil and Telugu, the difficulty is further increased by the lack of available resources. YouTube functions as both a video-sharing platform and a social media network. YouTube allows users to establish profiles an

不能约

Sales Forecasting from Group Conversation Using Natural Language Processingcale research, receive a more objective and accurate analysis, increase customer satisfaction, develop a better understanding of the industry, and empower employees. Forecasting future sales by projecting the number of products or services a sales unit sell is known as sales forecasting. The system