In this work, we provide a survey of active learning (AL) for its applications in natural
language processing (NLP). In addition to a fine-grained categorization of query strategies …

Multi-Task Learning (MTL) networks have emerged as a promising method for transferring
learned knowledge across different tasks. However, MTL must deal with challenges such as …

Recent Active Learning (AL) approaches in Natural Language Processing (NLP) proposed
using off-the-shelf pretrained language models (LMs). In this paper, we argue that these LMs …

The information extraction process includes Semantic Role Labeling (SRL) as one of its sub-
tasks. SRL aims to determine the semantic role of each entity within a sentence by …

Learning-based solutions for vision tasks require a large amount of labeled training data to
ensure their performance and reliability. In single-task vision-based settings, inconsistency …

Active learning seeks to achieve strong performance with fewer training samples. It does this
by iteratively asking an oracle to label newly selected samples in a human-in-the-loop …

Automated medical named entity recognition and normalization are fundamental for
constructing knowledge graphs and building QA systems. When it comes to medical text, the …

Multi-task learning, in which several tasks are jointly learned by a single model, allows NLP
models to share information from multiple annotations and may facilitate better predictions …

Active Learning (AL) is a method to iteratively select data for annotation from a pool of
unlabeled data, aiming to achieve better model performance than random selection …

Social media provide a rich source of data that can be mined and used for a wide variety of
research purposes. However, annotating this data can be expensive, yet necessary for state …