Related papers: Comparing effectiveness of regularization methods …
Text simplification (TS) refers to the process of reducing the complexity of a text while retaining its original meaning and key information. Existing work only shows that large language models (LLMs) have outperformed supervised…
Curriculum learning can improve neural network training by guiding the optimization to desirable optima. We propose a novel curriculum learning approach for image classification that adapts the loss function by changing the label…
We propose a semi-supervised text classifier based on self-training using one positive and one negative property of neural networks. One of the weaknesses of self-training is the semantic drift problem, where noisy pseudo-labels accumulate…
Few-shot learning benchmarks are critical for evaluating modern NLP techniques. It is possible, however, that benchmarks favor methods which easily make use of unlabeled text, because researchers can use unlabeled text from the test set to…
Active learning is a paradigm aimed at reducing the annotation effort by training the model on actively selected informative and/or representative samples. Another paradigm to reduce the annotation effort is self-training that learns from a…
Complementary-label learning is a weakly supervised learning problem in which each training example is associated with one or multiple complementary labels indicating the classes to which it does not belong. Existing consistent approaches…
Labeling a classification dataset implies to define classes and associated coarse labels, that may approximate a smoother and more complicated ground truth. For example, natural images may contain multiple objects, only one of which is…
We study the problem of learning an adversarially robust predictor to test time attacks in the semi-supervised PAC model. We address the question of how many labeled and unlabeled examples are required to ensure learning. We show that…
The strength of machine learning models stems from their ability to learn complex function approximations from data; however, this strength also makes training deep neural networks challenging. Notably, the complex models tend to memorize…
Representing a true label as a one-hot vector is a common practice in training text classification models. However, the one-hot representation may not adequately reflect the relation between the instances and labels, as labels are often not…
Given a task, human learns from easy to hard, whereas the model learns randomly. Undeniably, difficulty insensitive learning leads to great success in NLP, but little attention has been paid to the effect of text difficulty in NLP. In this…
Text classification is the most basic natural language processing task. It has a wide range of applications ranging from sentiment analysis to topic classification. Recently, deep learning approaches based on CNN, LSTM, and Transformers…
Text clustering serves as a fundamental technique for organizing and interpreting unstructured textual data, particularly in contexts where manual annotation is prohibitively costly. With the rapid advancement of Large Language Models…
Unsupervised text embedding methods, such as Skip-gram and Paragraph Vector, have been attracting increasing attention due to their simplicity, scalability, and effectiveness. However, comparing to sophisticated deep learning architectures…
We investigate how well large language models (LLMs) generalize across different task difficulties, a key question for effective data curation and evaluation. Existing research is mixed regarding whether training on easier or harder data…
Overconfidence has been shown to impair generalization and calibration of a neural network. Previous studies remedy this issue by adding a regularization term to a loss function, preventing a model from making a peaked distribution. Label…
Modern classification models tend to struggle when the amount of annotated data is scarce. To overcome this issue, several neural few-shot classification models have emerged, yielding significant progress over time, both in Computer Vision…
Most of the literature around text classification treats it as a supervised learning problem: given a corpus of labeled documents, train a classifier such that it can accurately predict the classes of unseen documents. In industry, however,…
One advantage of neural ranking models is that they are meant to generalise well in situations of synonymity i.e. where two words have similar or identical meanings. In this paper, we investigate and quantify how well various ranking models…
The exponential growth of data generated on the Internet in the current information age is a driving force for the digital economy. Extraction of information is the major value in an accumulated big data. Big data dependency on statistical…