Related papers: When Attention Collapses: Residual Evidence Modeli…

Scientific claim verification, the task of determining whether claims are entailed by scientific evidence, is fundamental to establishing discoveries in evidence while preventing misinformation. This process involves evaluating each…

Attention is a very efficient way to model the relationship between two sequences by comparing how similar two intermediate representations are. Initially demonstrated in NMT, it is a standard in all NLU tasks today when efficient…

The integrity of behavioral and social-science surveys depends on detecting inattentive respondents who provide random or low-effort answers. Traditional safeguards, such as attention checks, are often costly, reactive, and inconsistent. We…

Adversarial examples -- inputs with imperceptible perturbations that fool neural networks -- remain one of deep learning's most perplexing phenomena despite nearly a decade of research. While numerous defenses and explanations have been…

Observational data is increasingly used as a means for making individual-level causal predictions and intervention recommendations. The foremost challenge of causal inference from observational data is hidden confounding, whose presence…

Multiple intent detection and slot filling are two fundamental and crucial tasks in spoken language understanding. Motivated by the fact that the two tasks are closely related, joint models that can detect intents and extract slots…

Detecting partially occluded objects is a difficult task. Our experimental results show that deep learning approaches, such as Faster R-CNN, are not robust at object detection under occlusion. Compositional convolutional neural networks…

Profile-based intent detection and slot filling are important tasks aimed at reducing the ambiguity in user utterances by leveraging user-specific supporting profile information. However, research in these two tasks has not been extensively…

Study samples often differ from the target populations of inference and policy decisions in non-random ways. Researchers typically believe that such departures from random sampling -- due to changes in the population over time and space, or…

The appearance of the same object may vary in different scene images due to perspectives and occlusions between objects. Humans can easily identify the same object, even if occlusions exist, by completing the occluded parts based on its…

Intelligent systems possess a crucial characteristic of breaking complicated problems into smaller reusable components or parts and adjusting to new tasks using these part representations. However, current part-learners encounter…

Despite remarkable progress made in natural language processing, even the state-of-the-art models often make incorrect predictions. Such predictions hamper the reliability of systems and limit their widespread adoption in real-world…

Semisupervised methods inevitably invoke some assumption that links the marginal distribution of the features to the regression function of the label. Most commonly, the cluster or manifold assumptions are used which imply that the…

Recently, neural module networks (NMNs) have yielded ongoing success in answering compositional visual questions, especially those involving multi-hop visual and logical reasoning. NMNs decompose the complex question into several sub-tasks…

Controlling the patterns a model learns is essential to preventing reliance on irrelevant or misleading features. Such reliance on irrelevant features, often called shortcut features, has been observed across domains, including medical…

In tasks like semantic parsing, instruction following, and question answering, standard deep networks fail to generalize compositionally from small datasets. Many existing approaches overcome this limitation with model architectures that…

Modern recommender systems employ various sequential modules such as self-attention to learn dynamic user interests. However, these methods are less effective in capturing collaborative and transitional signals within user interaction…

Attention mechanisms form a core component of several successful deep learning architectures, and are based on one key idea: ''The output depends only on a small (but unknown) segment of the input.'' In several practical applications like…

In-context learning (ICL) is an emerging capability of large autoregressive language models where a few input-label demonstrations are appended to the input to enhance the model's understanding of downstream NLP tasks, without directly…

Learning predictive models for unlabeled spatiotemporal data is challenging in part because visual dynamics can be highly entangled in real scenes, making existing approaches prone to overfit partial modes of physical processes while…