Related papers: An Interactive Human-Machine Learning Interface fo…

Attention guidance is an approach to addressing dataset bias in deep learning, where the model relies on incorrect features to make decisions. Focusing on image classification tasks, we propose an efficient human-in-the-loop system to…

The work discusses the use of machine learning algorithms for anomaly detection in medical image analysis and how the performance of these algorithms depends on the number of annotators and the quality of labels. To address the issue of…

We present an elegant and effective approach for addressing limitations in existing multi-label classification models by incorporating interaction matching, a concept shown to be useful for ad-hoc search result ranking. By performing soft…

Machine learning methods adapt the parameters of a model, constrained to lie in a given model class, by using a fixed learning procedure based on data or active observations. Adaptation is done on a per-task basis, and retraining is needed…

Speech emotion recognition systems often predict a consensus value generated from the ratings of multiple annotators. However, these models have limited ability to predict the annotation of any one person. Alternatively, models can learn to…

This paper proposes a novel training scheme for fast matching models in Search Ads, which is motivated by the real challenges in model training. The first challenge stems from the pursuit of high throughput, which prohibits the deployment…

Span annotation - annotating specific text features at the span level - can be used to evaluate texts where single-score metrics fail to provide actionable feedback. Until recently, span annotation was done by human annotators or fine-tuned…

Despite the recent advances in multi-task learning of dense prediction problems, most methods rely on expensive labelled datasets. In this paper, we present a label efficient approach and look at jointly learning of multiple dense…

Robots are required to autonomously respond to changing situations. Imitation learning is a promising candidate for achieving generalization performance, and extensive results have been demonstrated in object manipulation. However,…

As machine learning (ML) models are increasingly used in social domains to make consequential decisions about humans, they often have the power to reshape data distributions. Humans, as strategic agents, continuously adapt their behaviors…

We propose an interactive-predictive neural machine translation framework for easier model personalization using reinforcement and imitation learning. During the interactive translation process, the user is asked for feedback on uncertain…

Today, ground-truth generation uses data sets annotated by cloud-based annotation services. These services rely on human annotation, which can be prohibitively expensive. In this paper, we consider the problem of hybrid human-machine…

Learned object detection methods based on fusion of LiDAR and camera data require labeled training samples, but niche applications, such as warehouse robotics or automated infrastructure, require semantic classes not available in large…

Strong inductive biases give humans the ability to quickly learn to perform a variety of tasks. Although meta-learning is a method to endow neural networks with useful inductive biases, agents trained by meta-learning may sometimes acquire…

Learning from human demonstration is an effective approach for learning complex manipulation skills. However, existing approaches heavily focus on learning from passive human demonstration data for its simplicity in data collection.…

This study introduces a prescriptive annotation benchmark grounded in humanities research to ensure consistent, unbiased labeling of offensive language, particularly for casual and non-mainstream language uses. We contribute two newly…

High-quality human annotations are necessary for creating effective machine learning-driven stream processing systems. We study hybrid stream processing systems based on a Human-In-The-Loop Machine Learning (HITL-ML) paradigm, in which one…

Human-annotated labels and explanations are critical for training explainable NLP models. However, unlike human-annotated labels whose quality is easier to calibrate (e.g., with a majority vote), human-crafted free-form explanations can be…

Annotation is the labeling of data by human effort. Annotation is critical to modern machine learning, and Bloomberg has developed years of experience of annotation at scale. This report captures a wealth of wisdom for applied annotation…

This work describes a self-supervised data augmentation approach used to improve learning models' performances when only a moderate amount of labeled data is available. Multiple copies of the original model are initially trained on the…