Related papers: Classifying Math KCs via Task-Adaptive Pre-Trained…

Keyphrase boundary classification (KBC) is the task of detecting keyphrases in scientific articles and labelling them with respect to predefined types. Although important in practice, this task is so far underexplored, partly due to the…

Knowledge tracing (KT) refers to the problem of predicting future learner performance given their past performance in educational applications. Recent developments in KT using flexible deep neural network-based models excel at this task.…

Active learning has been shown to be an effective way to alleviate some of the effort required in utilising large collections of unlabelled data for machine learning tasks without needing to fully label them. The representation mechanism…

We propose ADAPT, a meta-learning algorithm that \emph{learns} task sampling proportions under an explicit token budget for multi-task instruction tuning. Instead of fixing task weights by hand, \adapt{} maintains a continuous distribution…

Although pre-trained language models (PLMs) have achieved state-of-the-art performance on various natural language processing (NLP) tasks, they are shown to be lacking in knowledge when dealing with knowledge driven tasks. Despite the many…

Personalized instruction aims to provide learners with support that adapts to their individual knowledge and progress toward learning objectives. Discovering and tracing Knowledge Components (KCs) is an important step in building accurate…

Self-training methods have been explored in recent years and have exhibited great performance in improving semi-supervised learning. This work presents a Simple instance-Adaptive self-Training method (SAT) for semi-supervised text…

In this paper, we aim to improve the performance of a deep learning model towards image classification tasks, proposing a novel anchor-based training methodology, named \textit{Online Anchor-based Training} (OAT). The OAT method, guided by…

Consider a scenario in which we have a huge labeled dataset ${\cal D}$ and a limited time to train some given learner using ${\cal D}$. Since we may not be able to use the whole dataset, how should we proceed? Questions of this nature…

This paper studies continual learning (CL) of a sequence of aspect sentiment classification (ASC) tasks. Although some CL techniques have been proposed for document sentiment classification, we are not aware of any CL work on ASC. A CL…

Open-ended questions in surveys are valuable because they do not constrain the respondent's answer, thereby avoiding biases. However, answers to open-ended questions are text data which are harder to analyze. Traditionally, answers were…

This paper investigates whether the power of the models pre-trained on text data, such as BERT, can be transferred to general token sequence classification applications. To verify pre-trained models' transferability, we test the pre-trained…

Data labeling in supervised learning is considered an expensive and infeasible tool in some conditions. The self-supervised learning method is proposed to tackle the learning effectiveness with fewer labeled data, however, there is a lack…

Graph Neural Networks (GNNs) have made significant advancements in node classification, but their success relies on sufficient labeled nodes per class in the training data. Real-world graph data often exhibits a long-tail distribution with…

This paper achieves state of the art results for the ICD code prediction task using the MIMIC-III dataset. This was achieved through the use of Clinical BERT (Alsentzer et al., 2019). embeddings and text augmentation and label balancing to…

Large pre-trained sentence encoders like BERT start a new chapter in natural language processing. A common practice to apply pre-trained BERT to sequence classification tasks (e.g., classification of sentences or sentence pairs) is by…

Accurate annotation of educational resources is crucial for effective personalized learning and resource recommendation in online education. However, fine-grained knowledge labels often overlap or share similarities, making it difficult for…

Task-adaptive pre-training (TAPT) alleviates the lack of labelled data and provides performance lift by adapting unlabelled data to downstream task. Unfortunately, existing adaptations mainly involve deterministic rules that cannot…

Computational social science (CSS) practitioners often rely on human-labeled data to fine-tune supervised text classifiers. We assess the potential for researchers to augment or replace human-generated training data with surrogate training…

The task of link prediction aims to solve the problem of incomplete knowledge caused by the difficulty of collecting facts from the real world. GCNs-based models are widely applied to solve link prediction problems due to their…