This paper introduces SoftEDA, a novel technique that applies soft labels to augmented data. Traditional Easy Data Augmentation (EDA) techniques can potentially damage the original meaning of the text, hurting…
Continue readingThe research paper presents L3Cube-IndicNews, a multilingual text classification corpus specifically focusing on news headlines and articles in Indian regional languages. This includes Hindi, Bengali, Marathi, Telugu, Tamil, Gujarati, Kannada,…
Continue readingThis article presents L3Cube-IndicNews, a multilingual text classification corpus aimed at creating a high-quality dataset for Indian regional languages. The focus is on news headlines and articles in 10 prominent…
Continue readingThe paper presents an approach to detecting violence-inciting texts on social media, a problem that has been exacerbated in low-resource settings due to sparse research and less data. The authors…
Continue readingThe article, ‘Efficient Trigger Word Insertion’, focuses on the threats posed by backdoor attacks on deep neural network models in the field of Natural Language Processing (NLP). The authors propose…
Continue readingThe paper introduces a method called Label-Aware Automatic Verbalizer (LAA V) to enhance the effectiveness of few-shot text classification. This technique augments manual labels to achieve better classification results. The…
Continue readingThis paper presents a new approach to multi-label text classification (MLTC) that doesn’t require extensive data annotation. The method uses a pre-trained language model to map input text into a…
Continue readingThe paper discusses the importance of deep learning methods in text classification due to the rapid growth of online information. Text classification which automatically sorts documents into predefined categories based…
Continue readingLooks like you're using an ad blocker. Please support us by disabling these ad blocker.
