Related papers: The Practical Challenges of Active Learning: Lesso…

Data generation and labeling are usually an expensive part of learning for robotics. While active learning methods are commonly used to tackle the former problem, preference-based learning is a concept that attempts to solve the latter by…

With a handful of demonstration examples, large-scale language models show strong capability to perform various tasks by in-context learning from these examples, without any fine-tuning. We demonstrate that in-context learning performance…

Telephone transcription data can be very noisy due to speech recognition errors, disfluencies, etc. Not only that annotating such data is very challenging for the annotators, but also such data may have lots of annotation errors even after…

Active learning is an important machine learning problem in reducing the human labeling effort. Current active learning strategies are designed from human knowledge, and are applied on each dataset in an immutable manner. In other words,…

The construction of high-quality datasets is a cornerstone of modern text-to-speech (TTS) systems. However, the increasing scale of available data poses significant challenges, including storage constraints. To address these issues, we…

Mining user-generated data often suffers from the lack of enough labeled data, short document lengths, and the informal user language. In this paper, we propose a novel active learning model to overcome these obstacles in the tasks tailored…

We present a new active learning algorithm that adaptively partitions the input space into a finite number of regions, and subsequently seeks a distinct predictor for each region, both phases actively requesting labels. We prove theoretical…

Activity-based learning helps students to learn through participation. A virtual codeathon activity, as part of this learning scheme, was conducted for 180 undergraduate students to focus on analysis and design of solutions to crucial…

Tactile perception is important for robotic systems that interact with the world through touch. Touch is an active sense in which tactile measurements depend on the contact properties of an interaction--e.g., velocity, force,…

Active Learning is concerned with the question of how to identify the most useful samples for a Machine Learning algorithm to be trained with. When applied correctly, it can be a very powerful tool to counteract the immense data…

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…

Humans can leverage hierarchical structures to split a task into sub-tasks and solve problems efficiently. Both imitation and reinforcement learning or a combination of them with hierarchical structures have been proven to be an efficient…

Active learning is commonly used to train label-efficient models by adaptively selecting the most informative queries. However, most active learning strategies are designed to either learn a representation of the data (e.g., embedding or…

In machine learning, active class selection (ACS) algorithms aim to actively select a class and ask the oracle to provide an instance for that class to optimize a classifier's performance while minimizing the number of requests. In this…

Active Learning (AL) has been a powerful paradigm for improving model efficiency and performance by selecting the most informative data points for labeling and training. In recent active learning frameworks, Large Language Models (LLMs)…

The cost of annotating transcriptions for large speech corpora becomes a bottleneck to maximally enjoy the potential capacity of deep neural network-based automatic speech recognition models. In this paper, we present a new training…

Designing machine intelligence to converse with a human user necessarily requires an understanding of how humans participate in conversation, and thus conversation modeling is an important task in natural language processing. New…

Continual learning strives to ensure stability in solving previously seen tasks while demonstrating plasticity in a novel domain. Recent advances in continual learning are mostly confined to a supervised learning setting, especially in NLP…

With advances in data-driven machine learning research, a wide variety of prediction models have been proposed to capture spatio-temporal features for the analysis of video streams. Recognising actions and detecting action transitions…

Active learning allows machine learning models to be trained using fewer labels while retaining similar performance to traditional supervised learning. An active learner selects the most informative data points, requests their labels, and…