Identifying the key order parameters that connect a protein's native structure to its dynamical and evolutionary behavior remains a central challenge. We introduce topological and geometrical metrics-specifically, writhe and Local Topological Energy (LTE)-to investigate these connections. Applying these tools to both present-day and ancestral forms of thioredoxin and β-lactamase, we show that LTE strongly correlates with established dynamical measures such as the Dynamical Flexibility Index (DFI). Remarkably, LTE distributions also track the evolutionary trajectories of these proteins, suggesting that the topological geometry of the native state encodes key aspects of both dynamics and evolution. Through molecular dynamics simulations, we further reveal critical shifts in the topological landscape of proteins, providing a molecular mechanism by which functional evolution proceeds via alterations in conformational dynamics. Extending our analysis to over 100 proteins, we provide the first compelling evidence that topological descriptors derived from static structures can reliably predict dynamical behavior. In general, our findings demonstrate that simple geometrical metrics capture essential features of protein conformational landscapes, offering a powerful new approach to bridging protein structure, dynamics, and evolution.

Knowledge-dependent tasks typically use two sources of knowledge: parametric, learned at training time, and contextual, given as a passage at inference time.To understand how models use these sources together, we formalize the problem of knowledge conflicts, where the contextual information contradicts the learned information.Analyzing the behaviour of popular models, we measure their over-reliance on memorized information (the cause of hallucinations), and uncover important factors that exacerbate this behaviour.Lastly, we propose a simple method to mitigate over-reliance on parametric knowledge which minimizes hallucination and improves out-of-distribution generalization by 4% -7%.Our findings demonstrate the importance for practitioners to evaluate model tendency to hallucinate rather than read, and show that our mitigation strategy encourages generalization to evolving information (i.e., time-dependent queries).To encourage these practices, we have released our framework for generating knowledge conflicts.1

We propose a simple and efficient approach for pre-training deep learning models with application to slot filling tasks in spoken language understanding. The proposed approach leverages unlabeled data to train the models and is generic enough to work with any deep learning model. In this study, we consider the CNN2CRF architecture that contains Convolutional Neural Network (CNN) with Conditional Random Fields (CRF) as top layer, since it has shown great potential for learning useful representations for supervised sequence learning tasks. The proposed pre-training approach with this architecture learns the feature representations from both labeled and unlabeled data at the CNN layer, covering features that would not be observed in limited labeled data. At the CRF layer, the unlabeled data uses predicted classes of words as latent sequence labels together with labeled sequences. Latent labeled sequences, in principle, has the regularization effect on the labeled sequences, yielding a better generalized model. This allows the network to learn representations that are useful for not only slot tagging using labeled data but also learning dependencies both within and between latent clusters of unseen words. The proposed pre-training method with the CRF2CNN architecture achieves significant gains with respect to the strongest semi-supervised baseline.

Spoken language understanding and dialog management have emerged as key technologies in interacting with personal digital assistants (PDAs). The coverage, complexity, and the scale of PDAs are much larger than previous conversational understanding systems. As such, new problems arise. In this paper, we provide an overview of the language understanding and dialog management capabilities of PDAs, focusing particularly on Cortana, Microsoft's PDA. We explain the system architecture for language understanding and dialog management for our PDA, indicate how it differs with prior state-of-the-art systems, and describe key components. We also report a set of experiments detailing system performance on a variety of scenarios and tasks. We describe how the quality of user experiences are measured end-to-end and also discuss open issues.