Related papers: ARAIDA: Analogical Reasoning-Augmented Interactive…
Supervised Deep Learning has been highly successful in recent years, achieving state-of-the-art results in most tasks. However, with the ongoing uptake of such methods in industrial applications, the requirement for large amounts of…
Existing audio question answering benchmarks largely emphasize sound event classification or caption-grounded queries, often enabling models to succeed through shortcut strategies, short-duration cues, lexical priors, dataset-specific…
In order to perform multimodal fusion of heterogeneous signals, we need to understand their interactions: how each modality individually provides information useful for a task and how this information changes in the presence of other…
Interior design often struggles to capture the subtleties of client experience, leaving gaps between what clients feel and what designers can act upon. We present AIDED, a designer-AI co-design workflow that integrates multimodal client…
Training models that can perform well on various NLP tasks require large amounts of data, and this becomes more apparent with nuanced tasks such as anaphora and conference resolution. To combat the prohibitive costs of creating manual gold…
We present a lightweight annotation tool, the Data AnnotatoR Tool (DART), for the general task of labeling structured data with textual descriptions. The tool is implemented as an interactive application that reduces human efforts in…
In offline reinforcement learning (RL), an RL agent learns to solve a task using only a fixed dataset of previously collected data. While offline RL has been successful in learning real-world robot control policies, it typically requires…
We introduce a new algorithm for approximation by rational functions on a real or complex set of points, implementable in 40 lines of Matlab and requiring no user input parameters. Even on a disk or interval the algorithm may outperform…
This paper develops and implements a scalable methodology for (a) estimating the noisiness of labels produced by a typical crowdsourcing semantic annotation task, and (b) reducing the resulting error of the labeling process by as much as…
To offer accurate and diverse recommendation services, recent methods use auxiliary information to foster the learning process of user and item representations. Many SOTA methods fuse different sources of information (user, item, knowledge…
Imitation learning has shown promise in learning from large-scale real-world datasets. However, pretrained policies usually perform poorly without sufficient in-domain data. Besides, human-collected demonstrations entail substantial labour…
Deep neural networks are vulnerable to adversarial examples. Adversarial training (AT) is an effective defense against adversarial examples. However, AT is prone to overfitting which degrades robustness substantially. Recently, data…
Human annotation of natural language facilitates standardized evaluation of natural language processing systems and supports automated feature extraction. This document consists of instructions for annotating the temporal information in…
High-quality data annotation is an essential but laborious and costly aspect of developing machine learning-based software. We explore the inherent tradeoff between annotation accuracy and cost by detecting and removing minority reports --…
Active learning can play an important role in low-resource settings (i.e., where annotated data is scarce), by selecting which instances may be more worthy to annotate. Most active learning approaches for Machine Translation assume the…
Annotated data plays a critical role in Natural Language Processing (NLP) in training models and evaluating their performance. Given recent developments in Large Language Models (LLMs), models such as ChatGPT demonstrate zero-shot…
Test collections are information-retrieval tools that allow researchers to quickly and easily evaluate ranking algorithms. While test collections have become an integral part of IR research, the process of data creation involves significant…
This paper aims to reduce the time to annotate images for panoptic segmentation, which requires annotating segmentation masks and class labels for all object instances and stuff regions. We formulate our approach as a collaborative process…
Developers' API needs should be more pragmatic, such as seeking suggestive, explainable, and extensible APIs rather than the so-called best result. Existing API search research cannot meet these pragmatic needs because they are solely…
We present and evaluate an approach for human-in-the-loop specification of shape reconstruction with annotations for basic robot-object interactions. Our method is based on the idea of model annotation: the addition of simple cues to an…