After over a century of internal combustion engines ruling the transport sector, electric vehicles appear to be on the verge of gaining traction due to a slew of advantages, including lower operating costs and lower CO2 emissions. By using the Vehicle-to-Grid (or Grid-to-Vehicle if Electric vehicles (EVs) are utilized as load) approach, EVs can operate as both a load and a source. Primary frequency regulation and congestion management are two essential characteristics of this technology that are added to an industrial microgrid. Industrial Microgrids are made up of different energy sources such as wind farms and PV farms, storage systems, and loads. EVs have gained a lot of interest as a technique for frequency management because of their ability to regulate quickly. Grid reliability depends on this quick reaction. Different contingency, state of charge of the electric vehicles, and a varying number of EVs in an EV fleet are considered in this work, and a proposed control scheme for frequency management is presented. This control scheme enables bidirectional power flow, allowing for primary frequency regulation during the various scenarios that an industrial microgrid may encounter over the course of a 24-h period. The presented controller will provide dependable frequency regulation support to the industrial microgrid during contingencies, as will be demonstrated by simulation results, achieving a more reliable system. However, simulation results will show that by increasing a number of the EVs in a fleet for the Vehicle-to-Grid approach, an industrial microgrid\'s frequency can be enhanced even further.

Distractors are important in learning evaluation. This paper surveys distractor generation tasks using English multiple-choice question datasets for textual and multimodal contexts. In particular, this paper presents a thorough literature review of the recent studies on distractor generation tasks, discusses multiple choice components and their characteristics, analyzes the related datasets, and summarizes the evaluation metrics of distractor generation. Our investigation reveals that more than half of datasets are human-generated from educational sources in specific domains such as Science and English, which are largely text-based, with a lack of open domain and multimodal datasets.

Code switching (CS) is a very common phenomenon in written and spoken communication but one that is handled poorly by many natural language processing applications. Looking to the application of building CS corpora, we explore CS language identification (LID) for corpus building. We make the task more realistic by scaling it to more languages and considering models with simpler architectures for faster inference. We also reformulate the task as a sentence-level multi-label tagging problem to make it more tractable. Having defined the task, we investigate three reasonable models for this task and define metrics which better reflect desired performance. We present empirical evidence that no current approach is adequate and finally provide recommendations for future work in this area.

Named Entity Recognition (NER) is a key information extraction task with a long-standing tradition. While recent studies address and aim to correct annotation errors via re-labeling efforts, little is known about the sources of human label variation, such as text ambiguity, annotation error, or guideline divergence. This is especially the case for high-quality datasets and beyond English CoNLL03. This paper studies disagreements in expert-annotated named entity datasets for three languages: English, Danish, and Bavarian. We show that text ambiguity and artificial guideline changes are dominant factors for diverse annotations among high-quality revisions. We survey student annotations on a subset of difficult entities and substantiate the feasibility and necessity of manifold annotations for understanding named entity ambiguities from a distributional perspective.

Context-aware Machine Translation aims to improve translations of sentences by incorporating surrounding sentences as context. Towards this task, two main architectures have been applied, namely single-encoder (based on concatenation) and multi-encoder models. In this study, we show that a special case of multi-encoder architecture, where the latent representation of the source sentence is cached and reused as the context in the next step, achieves higher accuracy on the contrastive datasets (where the models have to rank the correct translation among the provided sentences) and comparable BLEU and COMET scores as the single- and multi-encoder approaches. Furthermore, we investigate the application of Sequence Shortening to the cached representations. We test three pooling-based shortening techniques and introduce two novel methods - Latent Grouping and Latent Selecting, where the network learns to group tokens or selects the tokens to be cached as context. Our experiments show that the two methods achieve competitive BLEU and COMET scores and accuracies on the contrastive datasets to the other tested methods while potentially allowing for higher interpretability and reducing the growth of memory requirements with increased context size.

Pre-trained language models (LMs) perform well in In-Topic setups, where training and testing data come from the same topics. However, they face challenges in Cross-Topic scenarios where testing data is derived from distinct topics -- such as Gun Control. This study analyzes various LMs with three probing-based experiments to shed light on the reasons behind the In- vs. Cross-Topic generalization gap. Thereby, we demonstrate, for the first time, that generalization gaps and the robustness of the embedding space vary significantly across LMs. Additionally, we assess larger LMs and underscore the relevance of our analysis for recent models. Overall, diverse pre-training objectives, architectural regularization, or data deduplication contribute to more robust LMs and diminish generalization gaps. Our research contributes to a deeper understanding and comparison of language models across different generalization scenarios.

There is an intricate relation between the properties of an image and how humans behave while describing the image. This behavior shows ample variation, as manifested in human signals such as eye movements and when humans start to describe the image. Despite the value of such signals of visuo-linguistic variation, they are virtually disregarded in the training of current pretrained models, which motivates further investigation. Using a corpus of Dutch image descriptions with concurrently collected eye-tracking data, we explore the nature of the variation in visuo-linguistic signals, and find that they correlate with each other. Given this result, we hypothesize that variation stems partly from the properties of the images, and explore whether image representations encoded by pretrained vision encoders can capture such variation. Our results indicate that pretrained models do so to a weak-to-moderate degree, suggesting that the models lack biases about what makes a stimulus complex for humans and what leads to variations in human outputs.

Recent developments enable the quantification of causal control given a structural causal model (SCM). This has been accomplished by introducing quantities which encode changes in the entropy of one variable when intervening on another. These measures, named causal entropy and causal information gain, aim to address limitations in existing information theoretical approaches for machine learning tasks where causality plays a crucial role. They have not yet been properly mathematically studied. Our research contributes to the formal understanding of the notions of causal entropy and causal information gain by establishing and analyzing fundamental properties of these concepts, including bounds and chain rules. Furthermore, we elucidate the relationship between causal entropy and stochastic interventions. We also propose definitions for causal conditional entropy and causal conditional information gain. Overall, this exploration paves the way for enhancing causal machine learning tasks through the study of recently-proposed information theoretic quantities grounded in considerations about causality.

Prior research on AI-assisted human decision-making has explored several different explainable AI (XAI) approaches. A recent paper has proposed a paradigm shift calling for hypothesis-driven XAI through a conceptual framework called evaluative AI that gives people evidence that supports or refutes hypotheses without necessarily giving a decision-aid recommendation. In this paper we describe and evaluate an approach for hypothesis-driven XAI based on the Weight of Evidence (WoE) framework, which generates both positive and negative evidence for a given hypothesis. Through human behavioural experiments, we show that our hypothesis-driven approach increases decision accuracy, reduces reliance compared to a recommendation-driven approach and an AI-explanation-only baseline, but with a small increase in under-reliance compared to the recommendation-driven approach. Further, we show that participants used our hypothesis-driven approach in a materially different way to the two baselines.

Directional wavelet dictionaries are hierarchical representations which efficiently capture and segment information across scale, location and orientation. Such representations demonstrate a particular affinity to physical signals, which often exhibit highly anisotropic, localised multiscale structure. Many physically important signals are observed over spherical domains, such as the celestial sky in cosmology. Leveraging recent advances in computational harmonic analysis, we design new highly distributable and automatically differentiable directional wavelet transforms on the $2$-dimensional sphere $\mathbb{S}^2$ and $3$-dimensional ball $\mathbb{B}^3 = \mathbb{R}^+ \times \mathbb{S}^2$ (the space formed by augmenting the sphere with the radial half-line). We observe up to a $300$-fold and $21800$-fold acceleration for signals on the sphere and ball, respectively, compared to existing software, whilst maintaining 64-bit machine precision. Not only do these algorithms dramatically accelerate existing spherical wavelet transforms, the gradient information afforded by automatic differentiation unlocks many data-driven analysis techniques previously not possible for these spaces. We publicly release both S2WAV and S2BALL, open-sourced JAX libraries for our transforms that are automatically differentiable and readily deployable both on and over clusters of hardware accelerators (e.g. GPUs & TPUs).